Developer-tools MCP server

Fallow

Version history of discovered tools, schemas, and declared agent authority.

View watchlist

DistributionDistribution: npm
Packagefallow
Latest analyzed version3.43.2
Current tool count44
Latest analysisNov 16, 2026
Package source

OBSERVED INTERFACE

Capability surface

Modelara’s observed declarations are shown separately from its derived effect classifications.

3 releases analyzed3.43.0 → 3.43.2Latest: 3.43.2
  • read39
  • write4
  • destructive1
  • unknown0

Unknown means Valyd could not determine the capability's effect confidently from the declared interface and static evidence. It is not treated as safe.

Package
fallow@3.43.2
Registry
npm
Published
Nov 16, 2026
Integrity
sha512-ibOZSDgDZLIHYFWmxtF+JkdQEdcyTxgpGojtNbB7oJTW1jYyFc87lqUYVN3ZFEXHLBgysU+rcQ37v4x8kl3YIw==
Analyzer
modelara v0.1.8 · policy not recorded
Repository
https://github.com/fallow-rs/fallow

44 capabilities

CapabilityTypeDerived effectFirst observed in Valyd coverageLast changed
analyzefallow-rs-fallow:tool:analyze
Observed interface and hashes

Analyze a TypeScript/JavaScript project for unused code and dependency cycles. On a Rust root, it runs `cargo fallow check` (deps, visibility; no score) and takes only root. Detects unused files, exports, types, dependencies, enum/class members, unresolved imports, unlisted dependencies, duplicate exports, circular dependencies, re-export cycles (barrel files that form a structural loop, silently breaking re-exports), package cycles (workspace packages that import each other in a loop), boundary violations, rule-pack policy violations (banned calls, imports, and catalogue-derived effects declared via the rulePacks config key), stale suppression comments, missing suppression reasons when rules.require-suppression-reason is enabled, unused pnpm catalog entries (entries in pnpm-workspace.yaml `catalog:` / `catalogs:` not referenced by any workspace package), empty pnpm catalog groups, unresolved catalog references (workspace package.json declares `catalog:` but the catalog has no entry), unused dependency overrides (entries in `pnpm-workspace.yaml#overrides`, `package.json#pnpm.overrides`, top-level `package.json#overrides`, or Bun `package.json#resolutions` whose target package no workspace package declares and the active readable lockfile does not resolve), and misconfigured dependency overrides (unparsable key or empty value; the active package manager may reject or ignore the entry). Opt-in issue_types: ["private-type-leaks"] (API hygiene), ["deprecated-exports-in-use"] (@deprecated in use), ["absent-component-props"] (optional-prop review), ["constant-parameters"] (parameter review). Returns structured JSON with all issues found, grouped by issue type. Each finding has a stable `finding_id`; an id absent from a scoped or differently configured run means unknown, not resolved. For code duplication use find_dupes, for complexity hotspots use check_health. Supports baselines, regression detection, performance tuning, boundary_violations, and group_by. Read the `fallow://tools/analyze` resource for the boundary_violations alias, the group_by modes, and how to dispatch the `next_steps[]` follow-up commands.

Input schema

{
  "$defs": {
    "TypeAwareRequireParam": {
      "enum": [
        "best-effort",
        "complete"
      ],
      "type": "string"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "baseline": {
      "description": "Compare results against a saved baseline file. Only new issues (not in\nthe baseline) are reported. The response carries `baseline_staleness`:\nread `gate_trips` to see whether the baseline has entries that match\nnothing any more (re-save it with `save_baseline`), and read\n`change_scoped` first, because a run narrowed to part of the project can\nreport `matched_entries: 0` on a perfectly healthy baseline.\n`scope_reasons` names the channels that narrowed it.\n`unrecognised_format: true` means the file is not this command's baseline.\nIt suppressed nothing, so use another path and do not re-save.\n`saved_by` then names the command that wrote it, when fallow knows it.",
      "type": [
        "string",
        "null"
      ]
    },
    "boundary_violations": {
      "description": "Analyze only architecture boundary violations.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "fail_on_regression": {
      "description": "Fail if the issue count increased beyond `tolerance` compared to a\nregression baseline.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "file": {
      "description": "Scope analysis to these project-relative files instead of the whole project.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "finding_ids": {
      "description": "Report only these `finding_id` values. The response adds\n`finding_id_query`; a missing id is resolved only when `conclusive` is true.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "group_by": {
      "description": "Group findings by CODEOWNERS ownership, directory, workspace package, or\nGitLab CODEOWNERS section. Values: \"owner\", \"directory\", \"package\", \"section\".",
      "type": [
        "string",
        "null"
      ]
    },
    "include_entry_exports": {
      "description": "Report unused exports in entry files instead of auto-marking them as used.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "issue_types": {
      "description": "Issue types to include, for example `[\"unused-exports\", \"unused-files\"]`;\nempty or omitted means all registered issue types.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "no_package_baselines": {
      "description": "Ignore the per-package refs of `workspaces.changedSince` for this call,\nso every workspace package is analyzed in full scope. Use it to judge\nor save a whole-project baseline.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "regression_baseline": {
      "description": "Path to the regression baseline file.",
      "type": [
        "string",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "save_baseline": {
      "description": "Save current results as a baseline file for future comparisons. The path\nmust resolve inside the project root, its Git work tree, the CI workspace or a temp directory.\nA relative path resolves against the working directory of the MCP\nserver, not against `root`, so pass an absolute path.",
      "type": [
        "string",
        "null"
      ]
    },
    "save_regression_baseline": {
      "description": "Save the current issue counts as a regression baseline file at this\npath. An empty or absent value writes nothing: this tool cannot write the\ncounts into the fallow config. The path must resolve inside the project\nroot, its Git work tree, the CI workspace or a temp directory.\nA relative path resolves against the working directory of the MCP\nserver, not against `root`, so pass an absolute path.",
      "type": [
        "string",
        "null"
      ]
    },
    "show_cascade": {
      "description": "Keep the unused exports, types, class members and enum members of\nunused files. By default the report hides them and counts them in\n`cascade_hidden`. Passed through to the CLI's `--show-cascade` flag.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "tolerance": {
      "description": "Allowed issue count increase before a regression is flagged. Defaults to \"0\".",
      "type": [
        "string",
        "null"
      ]
    },
    "type_aware": {
      "description": "Refine project-wide public API findings with TypeScript symbol identity.\n`false` keeps the run syntactic, also when the config turns type-aware analysis on. `type_aware_projects` or `type_aware_require` turns it on and wins over `false`.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "type_aware_projects": {
      "description": "Explicit tsconfig paths for type-aware analysis.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "type_aware_require": {
      "anyOf": [
        {
          "$ref": "#/$defs/TypeAwareRequireParam"
        },
        {
          "type": "null"
        }
      ],
      "description": "Whether incomplete semantic evidence is advisory or gating."
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:2a170acb36310ca31a99c2512c244c897bc8f4e8d081d67cdafb02e216be5f15

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:cd8b36bb318b9f284d471f09ff7d2388a2d7f8b0bd8f30961bf081b06c08a3d1

Interface hash: sha256:39cb9d788b9ed24ce81d8644a0b2b4a83812d82304f4265a62b640f18a7cc0ea

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/analyze",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "analyze"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:7f66d346912435679a65649b79e02cbd6c2ea922d7a59757e847313e74f71ad2"
}
toolwrite3.43.0No change observed
auditfallow-rs-fallow:tool:audit
Observed interface and hashes

Audit changed files for dead code, complexity, duplication, styling, and diff risk. Purpose-built for reviewing AI-generated code. Combines the analyses scoped to changed files and returns a verdict (pass/warn/fail). Auto-detects the base branch if not specified. By default, audit runs the base ref too and gates only findings introduced by the changeset; inherited findings are annotated with introduced=false and counted under attribution. Set gate="all" or audit.gate="all" in config to gate every finding. Returns JSON with verdict, summary counts per category, attribution counts, and full issue details with actions array for remediation guidance. Per-analysis payloads nest under `dead_code`, `duplication`, and `complexity`; the `complexity` block carries the health sub-analysis output (audit JSON has no `health` key). The `diff_risk` section reports facts about the change itself, such as weakened tests, added suppressions, and a clone copy edited without its siblings. Styling analytics are on by default. Read the fallow://tools/audit guide for the diff-risk rules, styling, coverage, synthetic complexity units, grouping, baselines, runtime coverage, and `FALLOW_DIFF_FILE` scoping. Use this after generating code to verify quality before committing.

Input schema

{
  "$defs": {
    "BaselineModeParam": {
      "description": "How a health baseline matches findings, mirroring the CLI's\n`--baseline-mode` flag.",
      "enum": [
        "count",
        "identity"
      ],
      "type": "string"
    },
    "TypeAwareRequireParam": {
      "enum": [
        "best-effort",
        "complete"
      ],
      "type": "string"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "base": {
      "description": "Git ref to compare against (e.g., \"main\", \"HEAD~5\"). When unset, the\nbase is the git merge-base against the branch's upstream or the remote\ndefault (`origin/main`); set `FALLOW_AUDIT_BASE` in the server env to pin\nit.",
      "type": [
        "string",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "coverage": {
      "description": "Path to Istanbul coverage data (coverage-final.json) or raw V8 coverage\n(a `NODE_V8_COVERAGE` directory or one V8 JSON file) for accurate\nper-function CRAP scores in audit's health sub-analysis.\nWhen omitted, `FALLOW_COVERAGE` and then the `health.coverage` config\nfield apply, on the typed route and on the CLI fallback alike (where\nthe value is forwarded as `--coverage`), with the same precedence as\n`fallow audit --coverage`.",
      "type": [
        "string",
        "null"
      ]
    },
    "coverage_root": {
      "description": "Absolute prefix to strip from coverage data paths before CRAP matching.\nUse when coverage was generated in a different checkout root in CI or Docker.\nWhen omitted, `FALLOW_COVERAGE_ROOT` and then the `health.coverageRoot`\nconfig field apply, on the typed route and on the CLI fallback alike\n(where the value is forwarded as `--coverage-root`), with the same\nprecedence as `fallow audit --coverage-root`.",
      "type": [
        "string",
        "null"
      ]
    },
    "css": {
      "description": "Set `false` to skip styling analytics in audit. Unset or `true` uses\n`audit.css` from the config, which defaults to enabled.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "css_deep": {
      "description": "Enable or disable deep CSS analysis for audit: project-wide styling\nreachability and near-duplicate theme-token candidates, narrowed back to\nchanged anchors. Unset uses `audit.cssDeep` from the config, which\ndefaults to enabled; `true` or `false` overrides the config. No effect\nwhen styling analytics are off.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "dead_code_baseline": {
      "description": "Path to a dead-code baseline file (produced by `fallow dead-code\n--save-baseline`). When set, dead-code issues present in the\nbaseline are excluded from the audit verdict. Passed through to\nthe CLI's `--dead-code-baseline` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "dupes_baseline": {
      "description": "Path to a duplication baseline file (produced by `fallow dupes\n--save-baseline`). When set, clone groups present in the baseline\nare excluded from the audit verdict. Passed through to the CLI's\n`--dupes-baseline` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "explain_skipped": {
      "description": "Show per-pattern counts for skipped files: the default duplicates\nignores, and the built-in discovery ignores that removed source files\nfrom the walk.\nHuman-format only (human/markdown CLI output); MCP JSON responses suppress the note.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "gate": {
      "description": "Which findings affect the audit verdict. Values: \"new-only\" or \"all\".\nUnset uses `audit.gate` from the config, which defaults to \"new-only\".\nPassed through to the CLI's `--gate` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "group_by": {
      "description": "Group audit findings by CODEOWNERS ownership, directory, workspace\npackage, or GitLab CODEOWNERS section. Values: \"owner\", \"directory\",\n\"package\", \"section\". `section` attaches an `owners: string[]` array\nto each group in the JSON output. Passed through to the CLI's\n`--group-by` flag; propagates to all three sub-analyses (dead-code,\ndupes, health) that audit runs.",
      "type": [
        "string",
        "null"
      ]
    },
    "health_baseline": {
      "description": "Path to a health baseline file (produced by `fallow health\n--save-baseline`). When set, complexity findings present in the\nbaseline are excluded from the audit verdict. Passed through to\nthe CLI's `--health-baseline` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "health_baseline_mode": {
      "anyOf": [
        {
          "$ref": "#/$defs/BaselineModeParam"
        },
        {
          "type": "null"
        }
      ],
      "description": "How `health_baseline` matches complexity findings: \"count\" (per file\nand category, the CLI default) or \"identity\" (per function identity,\nstrict; requires a baseline saved with `--baseline-mode identity`).\nPassed through to the CLI's `--baseline-mode` flag."
    },
    "include_entry_exports": {
      "description": "Report unused exports in entry files instead of auto-marking them as\nused. Catches typos in framework exports (e.g. `meatdata` instead of\n`metadata`). Also configurable persistently via\n`includeEntryExports: true` in the fallow config file; this param\nORs with the config value. Passed through to the CLI's\n`--include-entry-exports` flag.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "max_crap": {
      "description": "Maximum CRAP score threshold (default 30.0). Functions meeting or\nexceeding this score cause audit to fail. Pair with `coverage` on\n`check_health` for accurate per-function CRAP; without Istanbul data\nfallow estimates coverage from the module graph. Passed through to\nthe CLI's `--max-crap` flag.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "min_invocations_hot": {
      "description": "Threshold for hot-path classification (default 100). Forwarded to\nthe sidecar when `runtime_coverage` is set. Passed through to the\nCLI's `--min-invocations-hot` flag.",
      "format": "uint64",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "only": {
      "description": "Run only these audit sub-analyses, with the values of bare `fallow\n--only`: `dead-code`, `architecture`, `dupes`, `health`. Replaces the\n`audit.deadCode`, `audit.health` and `audit.dupes` config selection.\nCannot be combined with `skip`.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "production": {
      "description": "Only analyze production code (excludes tests, stories, dev files).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production_dead_code": {
      "description": "Run only the dead-code sub-analysis in production mode.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production_dupes": {
      "description": "Run only the duplication sub-analysis in production mode.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production_health": {
      "description": "Run only the health sub-analysis in production mode.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "runtime_coverage": {
      "description": "Runtime coverage input (V8 directory, V8 JSON, or Istanbul coverage\nmap JSON). When set, audit adds runtime-coverage findings to the same\ncall: agents get the `hot-path-touched` verdict next to dead-code and\ncomplexity in one MCP call, without a second `check_runtime_coverage`\nstep. The verdict is informational. A single local capture is free.\nContinuous or multi-capture monitoring needs a license. Passed\nthrough to the CLI's `--runtime-coverage` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "show_cascade": {
      "description": "Keep the unused exports, types, class members and enum members of\nunused files. By default the report hides them and counts them in\n`cascade_hidden`. Passed through to the CLI's `--show-cascade` flag.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "skip": {
      "description": "Skip these audit sub-analyses, with the values of `only`. A skipped\nsub-analysis leaves the verdict; the response omits its block and sets\n`summary.dead_code_skipped`, `complexity_skipped` or\n`duplication_skipped`. A baseline for a skipped sub-analysis is an\nerror.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "type_aware": {
      "description": "Refine both audit sides with TypeScript symbol identity before attribution.\n`false` keeps the run syntactic, also when the config turns type-aware analysis on. `type_aware_projects` or `type_aware_require` turns it on and wins over `false`.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "type_aware_projects": {
      "description": "Explicit tsconfig paths for type-aware analysis.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "type_aware_require": {
      "anyOf": [
        {
          "$ref": "#/$defs/TypeAwareRequireParam"
        },
        {
          "type": "null"
        }
      ],
      "description": "Whether incomplete semantic evidence is advisory or gating."
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    },
    "worsened": {
      "description": "Verdict effect of an inherited complexity finding whose measured value\ngrew: \"warn\" (default), \"error\" (counts as introduced) or \"off\". Unset uses\n`audit.worsened`.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:355c9d4a1441052ba56102b33294184796e079b7577b60c8bc5a3ece41ac319b

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:ca358962d38f1fd510f3c054d83bfc0ad9a590628223011b9c67c49f83a8771e

Interface hash: sha256:56624e722a69584c50207557e991e42bcd5a867b6fd4eb5b6c01a8d91249669c

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/audit",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "audit"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:b8d4292cf51ef9d28d6b3693d5ab787a7ef369ae201e14a4ad0cbef3705c748f"
}
toolread3.43.0No change observed
check_architecturefallow-rs-fallow:tool:check_architecture
Observed interface and hashes

Check import cycles, boundary violations (with coverage and forbidden calls), and rule-pack policy violations. Returns the `kind: "architecture"` envelope: the finding arrays, `finding_id` values and actions of `analyze` for these issue types, with its own `schema_version`. Set `cycles`, `boundaries`, or `policy` to report one kind. Call `guard` before an edit and this tool after it. `baseline` takes a dead-code baseline. On a Rust root, it runs `cargo fallow boundaries`: `kind: "boundaries"`.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "baseline": {
      "description": "Saved dead-code baseline file; only new findings are reported.",
      "type": [
        "string",
        "null"
      ]
    },
    "boundaries": {
      "description": "Only boundary violations, coverage and forbidden calls.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "changed_since": {
      "description": "Report only findings in files changed since this git ref.",
      "type": [
        "string",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "cycles": {
      "description": "Only import cycles.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "file": {
      "description": "Project-relative files to scope the report to.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "group_by": {
      "description": "\"owner\", \"directory\", \"package\", or \"section\".",
      "type": [
        "string",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "policy": {
      "description": "Only rule-pack policy violations.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:7045b9bfdd423a1845048fc6c438cfd8e8ff2fdf528e8475a1558c5ce975676a

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:cf27c6a3ca70560b24f06d3ae897d840a228a5334a0afde5d0352db14e2e68b4

Interface hash: sha256:e0beb31a68e936b100a70000942f76963d72949efb97f8054561ac174dc2c9f9

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/check_architecture",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "check_architecture"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:bd36ae6645780b6d41efae985d8fcacad8ac20b8668b69061658133a91a71384"
}
toolread3.43.0No change observed
check_changedfallow-rs-fallow:tool:check_changed
Observed interface and hashes

Analyze only files changed since a git ref. Useful for incremental CI checks on pull requests. Returns the same structured JSON as analyze, but filtered to only include issues in changed files. Each finding keeps its `finding_id` from analyze; an id absent here means unknown, not resolved. Supports baseline comparisons (baseline/save_baseline), regression detection (fail_on_regression, tolerance, regression_baseline, save_regression_baseline), and performance tuning (no_cache, threads).

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "baseline": {
      "description": "Compare results against a saved baseline file. Only new issues (not in\nthe baseline) are reported. The response carries `baseline_staleness`:\nread `gate_trips` to see whether the baseline has entries that match\nnothing any more (re-save it with `save_baseline`), and read\n`change_scoped` first, because a run narrowed to part of the project can\nreport `matched_entries: 0` on a perfectly healthy baseline.\n`scope_reasons` names the channels that narrowed it.\n`unrecognised_format: true` means the file is not this command's baseline.\nIt suppressed nothing, so use another path and do not re-save.\n`saved_by` then names the command that wrote it, when fallow knows it.",
      "type": [
        "string",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "fail_on_regression": {
      "description": "Fail if the issue count increased beyond `tolerance` compared to a\nregression baseline.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "include_entry_exports": {
      "description": "Report unused exports in entry files instead of auto-marking them as used.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "regression_baseline": {
      "description": "Path to the regression baseline file.",
      "type": [
        "string",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "save_baseline": {
      "description": "Save current results as a baseline file for future comparisons. The path\nmust resolve inside the project root, its Git work tree, the CI workspace or a temp directory.\nA relative path resolves against the working directory of the MCP\nserver, not against `root`, so pass an absolute path.",
      "type": [
        "string",
        "null"
      ]
    },
    "save_regression_baseline": {
      "description": "Save the current issue counts as a regression baseline file at this\npath. An empty or absent value writes nothing: this tool cannot write the\ncounts into the fallow config. The path must resolve inside the project\nroot, its Git work tree, the CI workspace or a temp directory.\nA relative path resolves against the working directory of the MCP\nserver, not against `root`, so pass an absolute path.",
      "type": [
        "string",
        "null"
      ]
    },
    "show_cascade": {
      "description": "Keep the unused exports, types, class members and enum members of\nunused files. By default the report hides them and counts them in\n`cascade_hidden`. Passed through to the CLI's `--show-cascade` flag.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "since": {
      "description": "Git ref to compare against (e.g. \"main\", \"HEAD~5\"). Only files changed\nsince this ref are analyzed. Required.",
      "type": "string"
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "tolerance": {
      "description": "Allowed issue count increase before a regression is flagged. Defaults to \"0\".",
      "type": [
        "string",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "since"
  ],
  "type": "object"
}
sha256:d1b46aae9a3b3e21fcff941b9f6e53dde69490f52c357cb2feb7cbfb6d8f96b0

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:58fea07ceeb93dcc1b884538aad66a05c93cd01a762f15d85a6039859c62ad7d

Interface hash: sha256:2f068a5220a62a7c08b914d07bd32f49ec5d9cc52a325ef503ef78b09cccfcdd

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/check_changed",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "check_changed"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:ed784144a7b3a4d7d74e94446c57d20bf0f0f153dce1bc2d300fde570e43c12f"
}
toolwrite3.43.0No change observed
check_healthfallow-rs-fallow:tool:check_health
Observed interface and hashes

Check code health metrics (cyclomatic and cognitive complexity) for functions in the project. Returns structured JSON with complexity scores per function, sorted by severity. On a Rust root, it runs `cargo fallow complexity` (max_cyclomatic, max_cognitive; no score). Set score=true for a single 0-100 health score with letter grade (A/B/C/D/F); runs duplication analysis automatically, but the churn-backed hotspot penalty requires hotspots=true (or targets=true). Set min_score=N to fail only when the score drops below a threshold (CI quality gate); min_score is authoritative, so complexity findings become informational and min_score=0 never fails. Exit codes are not surfaced over MCP, but the verdict is: a gated run publishes `gate_outcomes`, where `health-min-score` and `health-min-severity` carry a status, whether it was enforced, and the numbers compared. min_severity composes with min_score. Set file_scores=true for per-file health scores (maintainability index, fan-in, fan-out, dead code ratio, complexity density, CRAP risk), sorted in risk-aware triage order so lower MI and higher CRAP risk appear first. Set css=true to add a `css_analytics` section (specificity hotspots, `!important` density, over-complex selectors, deep nesting, design-token sprawl, unreferenced custom properties and `@keyframes`); opt-in because it parses every project stylesheet. Set complexity_breakdown=true to add a per-decision-point `contributions[]` array to each complexity finding, so you can explain WHY a function scored high and which lines to refactor. Set coverage_gaps=true to explicitly include static test coverage gaps: runtime files and exports with no test dependency path (not line-level coverage). A provided config file may also enable coverage gaps via rules.coverage-gaps when no health sections are explicitly selected. Set hotspots=true to identify files that are both complex and frequently changing (combines git churn with complexity). Set churn_file to a `fallow-churn/v1` JSON path to power the churn-backed signals (hotspots, ownership, refactoring targets) from imported VCS history instead of git. Set ownership=true (implies hotspots) to attach per-file ownership signals: bus factor, contributor count, declared CODEOWNERS owner, ownership_state, drift, and unowned-hotspot flag. Use ownership_email_mode=raw|handle|anonymized|hash for author email privacy (default handle; hash is the legacy spelling for anonymized output). Set targets=true for ranked refactoring recommendations sorted by efficiency (quick wins first), with confidence scores and adaptive percentile-based thresholds. Set trend=true to compare current metrics against the most recent saved snapshot and show per-metric deltas with directional indicators (improving/declining/stable). Implies --score. Requires prior snapshots saved with save_snapshot. Set effort to control analysis depth: 'low' (fast, surface-level), 'medium' (balanced, default), or 'high' (thorough, all heuristics). Set summary=true to include a natural-language summary of findings alongside the structured JSON. Set coverage to a path to Istanbul-format coverage data (coverage-final.json from Jest, Vitest, c8, nyc) for accurate per-function CRAP scores instead of the default estimated coverage. CRAP findings carry a `coverage_source` discriminator and the summary reports whether emitted sources are uniform or mixed. Besides real functions, health scores synthetic `<template>`, `<snippet:NAME>`, `<module>`, and Angular `<component>` rollup units, each with its own suppression placement and dimension rules. Set runtime_coverage to a path (V8 coverage directory, V8 JSON file, or Istanbul JSON file) for merged runtime-coverage findings (a single local capture is free; continuous or multi-capture runtime monitoring requires an active license via `fallow license activate`). Runtime-coverage tuning: set min_invocations_hot=N to tune the hot-path threshold (default 100), min_observation_volume=N to tune the high-confidence verdict floor (default 5000), and low_traffic_threshold=RATIO to tune the active/low-traffic split (default 0.001). Set group_by to "owner" (CODEOWNERS), "directory", "package" (workspace), or "section" (GitLab CODEOWNERS `[Section]` headers, with `owners` metadata per group) to partition results. Each group recomputes its own metrics against its files. When config health.thresholdOverrides is set, health findings use the resolved local thresholds and JSON includes threshold_overrides state so agents can see active, stale, and full-run no-match exceptions. For code duplication use find_dupes, for changed-file review use audit, and for execution-backed dead-or-hot verdicts use check_runtime_coverage. Read the `fallow://tools/check_health` resource for the per-flag detail this summary omits: the per-group metrics, `css_analytics` contents, `contributions[]` entries, the React `react_hook_profile` and render-fan-in vital signs, churn-file import, `coverage_source` values, the synthetic `<template>` / `<snippet:NAME>` / `<module>` / `<component>` units and their suppression placements, and the `threshold_overrides` row semantics. Supports config, baseline comparisons, and performance tuning (no_cache, threads). Useful for identifying hard-to-maintain code and prioritizing refactoring.

Input schema

{
  "$defs": {
    "BaselineModeParam": {
      "description": "How a health baseline matches findings, mirroring the CLI's\n`--baseline-mode` flag.",
      "enum": [
        "count",
        "identity"
      ],
      "type": "string"
    },
    "EmailModeParam": {
      "description": "Privacy mode for author emails emitted by `--ownership`.",
      "enum": [
        "raw",
        "handle",
        "anonymized",
        "hash"
      ],
      "type": "string"
    },
    "TypeAwareRequireParam": {
      "enum": [
        "best-effort",
        "complete"
      ],
      "type": "string"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "baseline": {
      "description": "Compare results against a saved baseline file. Only new issues (not in the baseline) are reported.\n`summary.baseline_staleness` reports how much of the baseline still matches: read `gate_trips`\nto see whether entries have gone stale (re-save with `save_baseline`), and read `change_scoped`\nfirst, because a narrowed run can report `matched_entries: 0` on a healthy baseline.\n`scope_reasons` names the channels that narrowed it.\n`unrecognised_format: true` means the file is not this command's baseline.\nIt suppressed nothing, so use another path and do not re-save.\n`saved_by` then names the command that wrote it, when fallow knows it.",
      "type": [
        "string",
        "null"
      ]
    },
    "baseline_mode": {
      "anyOf": [
        {
          "$ref": "#/$defs/BaselineModeParam"
        },
        {
          "type": "null"
        }
      ],
      "description": "How `baseline` matches health findings and which buckets `save_baseline`\nwrites: \"count\" (per file and category, the CLI default) or \"identity\"\n(per function identity, strict; requires a baseline saved in identity\nmode). When refreshing a baseline that was saved in identity mode, pass\n\"identity\" to preserve its identity buckets: a count-mode save drops\nthem and is refused unless \"count\" is passed explicitly. Passed through\nto the CLI's `--baseline-mode` flag."
    },
    "changed_since": {
      "description": "Git ref to compare against. Only files changed since this ref are analyzed.",
      "type": [
        "string",
        "null"
      ]
    },
    "churn_file": {
      "description": "Import change history from a `fallow-churn/v1` JSON file instead of `git\nlog`, so `hotspots` / `ownership` / `targets` work on projects with no git\nrepository (Yandex Arc, Mercurial, Perforce). A small wrapper translates\nthe VCS log into the contract. Resolved relative to `root`. Powers the\nchurn-backed signals (hotspots, ownership, refactoring targets) only; the\n`since` window labels the header but does not filter imported events (the\nfile is authoritative).",
      "type": [
        "string",
        "null"
      ]
    },
    "complexity": {
      "description": "Show only complexity findings. By default all sections are shown; use this to select only complexity.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "complexity_breakdown": {
      "description": "Include the per-decision-point complexity breakdown (`contributions[]`) on\neach complexity finding. Each entry names the construct (if, else-if,\nSvelte await/then, loop, boolean operator, React hook density, wide prop\ncount, ...) and its cyclomatic/cognitive weight, so the agent can explain\nWHY a function scored high and which lines to refactor. JSX depth remains\ndescriptive `react_jsx_max_depth` context, not a contribution. Forwards\n`--complexity-breakdown`. Off by default to keep output lean.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "coverage": {
      "description": "Path to coverage data for accurate per-function CRAP scores: an Istanbul\nmap (coverage-final.json), a directory containing one, a raw V8 coverage\ndirectory (`NODE_V8_COVERAGE`), or a single V8 coverage JSON file.\nWhen omitted, `FALLOW_COVERAGE` and then the `health.coverage` config\nfield apply, on the typed route and on the CLI fallback alike, with the\nsame precedence as `fallow health --coverage`.",
      "type": [
        "string",
        "null"
      ]
    },
    "coverage_gaps": {
      "description": "Explicitly request static test coverage gaps: runtime files and exports with\nno test dependency path. A provided config file may also enable coverage\ngaps via `rules.coverage-gaps` when no health sections are explicitly\nselected.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "coverage_root": {
      "description": "Absolute prefix to strip from coverage data paths before prepending the project root.\nUse when coverage was generated in a different environment (CI runner, Docker).\nWhen omitted, `FALLOW_COVERAGE_ROOT` and then the `health.coverageRoot`\nconfig field apply, on the typed route and on the CLI fallback alike,\nwith the same precedence as `fallow health --coverage-root`.",
      "type": [
        "string",
        "null"
      ]
    },
    "css": {
      "description": "Add a structural CSS analytics section (`css_analytics`): specificity\nhotspots, `!important` density, over-complex selectors, deep nesting,\ndesign-token sprawl (distinct colors / font-sizes / z-indexes), and\nunreferenced custom-property / `@keyframes` cleanup candidates. Forwards\n`--css`. Opt-in because it reads and parses project stylesheets. Standard\nCSS is parsed structurally; Sass/Less sources are scanned only where\nfallow can stay conservative without expanding preprocessor semantics.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "effort": {
      "description": "Analysis effort level. Controls the depth of analysis: \"low\" (fast, surface-level),\n\"medium\" (balanced, default), \"high\" (thorough, includes all heuristics).",
      "type": [
        "string",
        "null"
      ]
    },
    "file_scores": {
      "description": "Show only per-file health scores, sorted by risk-aware triage concern:\nlower maintainability index and higher CRAP risk first.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "group": {
      "description": "Keep only the matching groups of a `group_by` run: exact group keys,\nglobs, and `!`-prefixed negations, comma-separated. Project-level\nsections are not filtered. Requires `group_by`. Passed through to the\nCLI's `--group` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "group_by": {
      "description": "Group health findings by CODEOWNERS ownership, directory, workspace\npackage, or GitLab CODEOWNERS section. Values: \"owner\", \"directory\",\n\"package\", \"section\". `section` attaches an `owners: string[]` array\nto each group. Passed through to the CLI's `--group-by` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "hotspots": {
      "description": "Show only hotspots: files that are both complex and frequently changing.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "low_traffic_threshold": {
      "description": "Fraction of `trace_count` below which an invoked function is\nclassified `low_traffic` rather than `active`. Expressed as a\ndecimal (0.001 = 0.1%). Inherits the sidecar default (0.001) when\nomitted. Takes effect only when `runtime_coverage` is also set;\nsilently ignored otherwise.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_cognitive": {
      "description": "Maximum cognitive complexity threshold. Functions exceeding this are reported.",
      "format": "uint16",
      "maximum": 65535,
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "max_crap": {
      "description": "Maximum CRAP score threshold (default 30.0). Functions meeting or\nexceeding this score are reported alongside complexity findings. Pair\nwith `coverage` for accurate per-function CRAP; without Istanbul data\nfallow estimates coverage from the module graph.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_cyclomatic": {
      "description": "Maximum cyclomatic complexity threshold. Functions exceeding this are reported.",
      "format": "uint16",
      "maximum": 65535,
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "max_file_lines": {
      "description": "Maximum physical lines per file (default 0, off). A longer file is\nreported as a complexity finding with `exceeded: \"file_lines\"`.\nPassed through to the CLI's `--max-file-lines` flag.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_commits": {
      "description": "Minimum commits for a file to appear in hotspot ranking.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_invocations_hot": {
      "description": "Minimum invocation count for a function to be classified as a hot\npath in runtime-coverage output. Inherits the CLI default (100)\nwhen omitted. Takes effect only when `runtime_coverage` is also\nset; silently ignored otherwise.",
      "format": "uint64",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_observation_volume": {
      "description": "Minimum total trace volume before the sidecar may emit high-confidence\n`safe_to_delete` or `review_required` verdicts. Below this threshold,\nconfidence is capped at `medium` to protect against overconfident\nverdicts on new or low-traffic services. Inherits the sidecar default\n(5000) when omitted. Takes effect only when `runtime_coverage` is\nalso set; silently ignored otherwise.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_score": {
      "description": "Fail if the health score is below this threshold (0–100). Implies --score.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "min_severity": {
      "description": "Only exit with error for findings at or above this severity (moderate, high, critical).",
      "type": [
        "string",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "ownership": {
      "description": "Attach ownership signals (bus factor, contributors, declared owner,\ndrift) to hotspot entries. Implies `hotspots`. Requires git.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "ownership_email_mode": {
      "anyOf": [
        {
          "$ref": "#/$defs/EmailModeParam"
        },
        {
          "type": "null"
        }
      ],
      "description": "Privacy mode for author emails when `ownership` is enabled.\nImplies `ownership`. Defaults to `handle` server-side when omitted."
    },
    "production": {
      "description": "Only analyze production code (excludes tests, stories, dev files).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "runtime_coverage": {
      "description": "Path to runtime coverage input. Accepts a V8 coverage directory\n(`NODE_V8_COVERAGE=...`), a single V8 coverage JSON file, or an\nIstanbul `coverage-final.json`. A single local capture is free and\nruns without a license; continuous or multi-capture runtime\nmonitoring (a directory containing multiple JSON dumps) requires an\nactive license. Run `fallow license activate --trial --email <addr>`\nto start a 30-day trial when you need continuous monitoring.\nRuntime coverage can exceed the default 120s MCP subprocess timeout\non large dumps; raise `FALLOW_TIMEOUT_SECS` accordingly.",
      "type": [
        "string",
        "null"
      ]
    },
    "save_baseline": {
      "description": "Save current results as a baseline file for future comparisons. The path\nmust resolve inside the project root, its Git work tree, the CI workspace or a temp directory.\nA relative path resolves against the working directory of the MCP\nserver, not against `root`, so pass an absolute path.",
      "type": [
        "string",
        "null"
      ]
    },
    "save_snapshot": {
      "description": "Save a vital signs snapshot. Provide a file path, or omit value for default (`.fallow/snapshots/{timestamp}.json`).\nThe path must resolve inside the project root, its Git work tree, the CI workspace or a temp directory.\nA relative path resolves against the working directory of the MCP\nserver, not against `root`, so pass an absolute path.",
      "type": [
        "string",
        "null"
      ]
    },
    "score": {
      "description": "Show only the project health score (0–100) with letter grade (A/B/C/D/F).\nRuns duplication analysis automatically; pair with `hotspots=true` (or\n`targets=true`) for the churn-backed hotspot penalty.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "since": {
      "description": "Git history window for hotspot analysis. Accepts durations (6m, 90d, 1y) or ISO dates.\nIt also sets the window for change coupling and change dispersion. When absent,\nhotspots read 6 months and change coupling and dispersion read 12 months.",
      "type": [
        "string",
        "null"
      ]
    },
    "sort": {
      "description": "Sort order for results (e.g., \"cyclomatic\", \"cognitive\", \"lines\", \"severity\").",
      "type": [
        "string",
        "null"
      ]
    },
    "summary": {
      "description": "Include a natural-language summary of findings alongside the structured JSON output.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "targets": {
      "description": "Show only refactoring targets: ranked recommendations based on complexity, coupling, churn, and dead code.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "top": {
      "description": "Number of top results to return.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "trend": {
      "description": "Compare current metrics against the most recent saved snapshot and show per-metric deltas.\nImplies --score. Reads from `.fallow/snapshots/`.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "trend_from": {
      "description": "Compare current metrics against this snapshot file instead of the newest\nfile in `.fallow/snapshots/`. Implies `trend`. With `group_by`, each group\nis compared by key when the snapshot holds the same grouping. A\nrelative path resolves against the working directory of the MCP\nserver, so pass an absolute path. Passed through to `--trend-from`.",
      "type": [
        "string",
        "null"
      ]
    },
    "type_aware": {
      "description": "Enable the TypeScript semantic backend.\n`false` keeps the run syntactic, also when the config turns type-aware analysis on. `type_aware_projects` or `type_aware_require` turns it on and wins over `false`.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "type_aware_projects": {
      "description": "Explicit tsconfig paths for type-aware analysis.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "type_aware_require": {
      "anyOf": [
        {
          "$ref": "#/$defs/TypeAwareRequireParam"
        },
        {
          "type": "null"
        }
      ],
      "description": "Whether incomplete semantic evidence is advisory or gating."
    },
    "type_coupling": {
      "description": "Include advisory project-local public-signature type coupling.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:f74fd69e1d98b94c4d6baa565e8a7038059ce98765eca43be9a9cec9fe9d39ba

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:1701e188aa0a6e6b1b27cc9bcb38a151db59e83a0acda8a8e82f386454559296

Interface hash: sha256:01e27b9dade2eb680b67823355173f2bb682d4e5bda7f213dfe45ca67b0c7dbe

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/check_health",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "check_health"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:8dbc9cb37ab9bb1569a2d438d51db47f4f36021f8dc865db558722ac676b8494"
}
toolwrite3.43.0No change observed
check_runtime_coveragefallow-rs-fallow:tool:check_runtime_coverage
Observed interface and hashes

Merge runtime-coverage data into the health report. Focused entry point for the runtime-coverage pipeline: pass a V8 coverage directory (`NODE_V8_COVERAGE=<dir>`), a single V8 coverage JSON file, or an Istanbul `coverage-final.json` via the required `coverage` field. A single local capture is free and runs without a license; continuous or multi-capture runtime monitoring (multiple JSON files in a V8 directory) requires an active license JWT (start a 30-day trial with `fallow license activate --trial --email <addr>`; check state with `fallow license status`). Returns structured JSON with a `runtime_coverage` block containing surfaced `findings` verdicts (`safe_to_delete` / `review_required` / `low_traffic` / `coverage_unavailable`), stable content-hash IDs (`fallow:prod:<hash>`), evidence, percentile-ranked hot paths (each with `start_line` and `end_line` so consumers can match against a PR diff), and on protocol-0.3+ sidecars a `summary.capture_quality` block that flags short-window captures. The sidecar may still classify other functions as `active`, but the CLI omits those from `runtime_coverage.findings` to keep the surfaced list actionable. Tunable via `min_invocations_hot` (hot-path threshold, default 100), `min_observation_volume` (high-confidence verdict floor, default 5000), and `low_traffic_threshold` (active/low_traffic split, default 0.001). `group_by` partitions results by CODEOWNERS / directory / package / section. PR-context behavior: when `FALLOW_DIFF_FILE` (path to a unified diff) is set in the agent's process environment, the top-level `runtime_coverage.verdict` promotes `hot-path-touched` over `cold-code-detected` so reviewers see the diff-tied signal first, AND every hot path is narrowed to functions whose `[start_line, end_line]` overlaps an added hunk. `FALLOW_CHANGED_SINCE` (git ref) also scopes (file-level). Without a change scope the verdict stays cold-code-primary and all hot paths are returned. The full unprioritized list is always in `runtime_coverage.signals[]` (kebab-case strings, severity-descending). Runtime coverage can exceed the default 120s MCP subprocess timeout on multi-megabyte dumps; raise `FALLOW_TIMEOUT_SECS` accordingly. For general complexity / hotspot / CRAP analysis without a production dump, use `check_health` instead.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "coverage": {
      "description": "Path to runtime coverage input. Accepts a V8 coverage directory\n(`NODE_V8_COVERAGE=<dir>`), a single V8 coverage JSON file, or an\nIstanbul `coverage-final.json`. Required.",
      "type": "string"
    },
    "group_by": {
      "description": "Group health findings by CODEOWNERS ownership, directory, workspace\npackage, or GitLab CODEOWNERS section. Values: \"owner\", \"directory\",\n\"package\", \"section\". `section` attaches an `owners: string[]` array\nto each group. Passed through to the CLI's `--group-by` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "low_traffic_threshold": {
      "description": "Fraction of `trace_count` below which an invoked function is\nclassified `low_traffic` rather than `active`. Expressed as a\ndecimal (0.001 = 0.1%). Inherits the sidecar default (0.001) when\nomitted.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_crap": {
      "description": "Maximum CRAP score threshold (default 30.0). Functions meeting or\nexceeding this score appear as findings alongside complexity violations.\nProduction V8 coverage yields the most accurate per-function CRAP\ninputs, making this flag especially useful on this tool.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_invocations_hot": {
      "description": "Minimum invocation count for a function to be classified as a hot\npath. Inherits the CLI default (100) when omitted.",
      "format": "uint64",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_observation_volume": {
      "description": "Minimum total trace volume before the sidecar may emit high-confidence\n`safe_to_delete` or `review_required` verdicts. Below this threshold,\nconfidence is capped at `medium` to protect against overconfident\nverdicts on new or low-traffic services. Inherits the sidecar default\n(5000) when omitted.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Only analyze production code (excludes tests, stories, dev files).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "top": {
      "description": "Show only the top N runtime findings, hot paths, file scores, and\nrefactoring targets. Passed through to the CLI's `--top` flag.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "coverage"
  ],
  "type": "object"
}
sha256:3215e87877dbee0b159c7091daa9e30465efd53f089ccd1bfc20afe7e475eb62

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:ac1a1cd272b77b5c1edb9df863b9b0e6d12420105ffe592e5f03272768bc1340

Interface hash: sha256:cd6b46ce7e4a03f29d1a3c6ead0ec1a48f01376974f1a83364e635e969bec813

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/check_runtime_coverage",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "check_runtime_coverage"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:261821853b6e8682e8871db51573641ccc7cc0a7069908ec504fe04695b3c1d4"
}
toolread3.43.0No change observed
code_executefallow-rs-fallow:tool:code_execute
Observed interface and hashes

Execute a bounded, read-only JavaScript Code Mode snippet against fallow's MCP host API. `code` must be a JavaScript function expression or function body that receives `{ fallow, root }` and returns a JSON-serializable value. The embedded sandbox exposes only a typed `fallow` object with read-only analysis calls: analyze, combined, checkChanged, checkArchitecture, securityCandidates, findDupes, projectInfo, traceExport, traceFile, impactClosure, traceDependency, traceClone, checkHealth, audit, explain, listBoundaries, featureFlags, impact, checkRuntimeCoverage, getHotPaths, getBlastRadius, getImportance, getCleanupCandidates, plus `fallow.run(tool, params)` for the same allowlist. Similar-code (15-minute timeouts) and mutation are excluded; use the standalone find_similar_code, inspect_similar_code, mutation_plan, and mutation_inspect MCP tools. Mutating fix tools are intentionally not exposed. The sandbox has no filesystem, network, module imports, process, require, Deno, Bun, or shell access, and no dynamic code compilation: eval, Function, and the async and generator function constructors are removed, including the `constructor` route reachable through function prototypes. `root` is injected into host calls that omit params.root. `timeout_ms` caps JS execution and subprocess-backed host calls. In Code Mode, analyze, checkArchitecture, securityCandidates, findDupes, impactClosure, checkHealth, audit, impact, checkRuntimeCoverage, getHotPaths, getBlastRadius, getImportance, and getCleanupCandidates stay subprocess-backed and are killed on timeout. Every other host call runs in this process, where `timeout_ms` both answers you on time and sets that call's cancellation token: the analysis is asked to stop rather than only abandoned. The stop is cooperative and has no upper bound, because a token set inside a long analysis stage is not read until that stage ends, so the work may still be winding down after the call returns, and while it is the next in-process call falls back to the killable subprocess. `max_output_bytes` caps the total fallow JSON read by host calls and, separately, the serialized snippet result: a larger result is refused with `ok:false`, `truncated:true`, `result_bytes`, and a short `result_preview` in place of the value, so return a projection rather than a whole report; an oversized thrown error message is clamped too, at `max_output_bytes` or 4096 bytes, whichever is larger, and reported with `truncated:true` and `error_bytes`. Host calls refused before dispatch (unknown tool name, malformed params, an output budget with nothing left) run nothing and do not spend the `max_host_calls` budget; `limits.max_rejected_host_calls` bounds how many of them `calls[]` records. Host calls are memoized for the duration of one snippet: repeating the same tool with the same params (key order does not matter) is served from that snippet's own cache, spends no `max_host_calls` slot and no output budget, and still appears in `calls[]` marked `cache_hit: true`; nothing is cached between invocations. The trace itself is bounded at `limits.max_recorded_calls` entries: beyond that the host calls still run and still return, only their trace entries are dropped, and `calls_omitted` reports how many, so a snippet looping one cached call cannot grow the response without limit. `fallow.all(requests)` fans out independent host calls in one go: `requests` is an array of `{ tool, params }` objects whose `tool` is the same wire name `fallow.run` takes, and the return value is an array positionally aligned with it whose elements are `{ ok: true, value }` or `{ ok: false, error }`, so one failing element never hides the others. Every batch element goes through the same tool validation, `root` injection, memoization, shared deadline, and output-byte accounting as a single call, and each element that actually dispatches spends one `max_host_calls` slot. The output budget is shared rather than per element: what is left of `max_output_bytes` is divided evenly across the dispatches a batch makes, so a fan-out reads at most `max_output_bytes` in total. A batch is refused whole, before anything runs, when an element is not an object carrying a `tool` string, when it holds more than `max_host_calls` elements, or when it needs more dispatches than the budget has left. The snippet stays synchronous, with no promises in the sandbox: `fallow.all` blocks until every element has resolved, overlapping the subprocess-backed elements while in-process ones run one at a time, so a fan-out cannot stack in-process analyses whose only stop is cooperative.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "code": {
      "description": "JavaScript function expression or function body. The function receives\n`{ fallow, root }` and must return a JSON-serializable value.",
      "maxLength": 20000,
      "minLength": 1,
      "type": "string"
    },
    "max_output_bytes": {
      "description": "Maximum total bytes of fallow JSON output that sandbox host calls may\nread. Defaults to 1000000 and is capped at 4000000.",
      "format": "uint",
      "maximum": 4000000,
      "minimum": 1024,
      "type": [
        "integer",
        "null"
      ]
    },
    "root": {
      "description": "Default project root injected into fallow host calls when their params\nomit `root`.",
      "type": [
        "string",
        "null"
      ]
    },
    "timeout_ms": {
      "description": "Overall sandbox timeout in milliseconds. Defaults to 5000 and is capped\nat 30000.",
      "format": "uint64",
      "maximum": 30000,
      "minimum": 1,
      "type": [
        "integer",
        "null"
      ]
    }
  },
  "required": [
    "code"
  ],
  "type": "object"
}
sha256:90b1c9c97bf0eaa6b7d277ef6b65ac72c69a9e5ef03bacf9c16c86081ec97c75

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:b600c7891da38676b7225922dc602c74d13983b1c7083a9774caef9a3046754f

Interface hash: sha256:512cb333f8f594ff59966f026e689cbe6539d094d1626213dad3344fdd32ae1a

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/code_execute",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "code_execute"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:4c608d2797671d6fff86e04f4da942bb180078c39bbd025fe19d5b8f458ec4a6"
}
toolread3.43.0No change observed
decision_surfacefallow-rs-fallow:tool:decision_surface
Observed interface and hashes

Surface the consequential structural DECISIONS a change embeds, each framed as a judgment question for a human with taste (`fallow decision-surface --format json`). The apex of the review brief and the single call that puts taste-decisions in front of a reviewer; separable and cheap, it runs the same changed-code analysis as the brief, NOT the full project pipeline. Returns `kind: "decision-surface"` with `schema_version`, a ranked `decisions[]` list, an optional `truncated` note, and `signal_count`. Each decision carries a `signal_id` (a deterministic anchor to the fallow-emitted candidate it frames; an agent decision whose `signal_id` fallow did not emit must be REJECTED, this is the anti-hallucination contract), a `category` (EXACTLY the SOLID-3: `coupling-boundary`, `public-api-contract`, `dependency`, nothing else), the framed `question`, the `anchor_file`/`anchor_line`, the `blast` (modules affected beyond the diff) and `consequence` rank, the routed `expert[]` (who to ask) with a `bus_factor_one` flag, and structured `actions[]` (`ask-expert`, `suppress`). The surface is CAPPED to a working-memory-sized handful (4 plus or minus 1, configurable via `max_decisions`, clamped to 3-5); decisions beyond the cap collapse into `truncated`. Every `coupling-boundary` and `public-api-contract` decision is suppressible with a `// fallow-ignore` comment on the anchor file (the `suppress` action carries the paste-ready comment); a `dependency` decision anchors on a `package.json`, which cannot carry a comment, so it has no `suppress` action. Always exits 0 (advisory, never a gate). Use `base` to pick the comparison point (defaults to the git merge-base). Use this to answer "what are the few decisions in this change that actually need human judgment?" rather than scanning the whole diff.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "base": {
      "description": "Git ref to compare against (e.g., \"main\", \"HEAD~5\"). When unset, the\nbase is the git merge-base against the branch's upstream or the remote\ndefault (`origin/main`); set `FALLOW_AUDIT_BASE` in the server env to pin\nit.",
      "type": [
        "string",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "max_decisions": {
      "description": "Cap on the number of consequential structural decisions surfaced (the\nworking-memory limit). Default 4; clamped to the 3-5 band (4 plus or minus\n1).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:8711ee650c1fdf4060b947136d4894902c764bec4f095132c63c6d19a0f6ce5b

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:fb54a06c6edfea9117151600261c74819c93f2d105a1e90ddc077403afcd31cd

Interface hash: sha256:2df1b17d6eaf9572be6b7013b02e255fb8c537245c9ac7e9859da4011cf3183a

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/decision_surface",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "decision_surface"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:348eac80b92ad45c2f004e4f6df4a7bd4a022b2018bad67a703cf01cd02c0bea"
}
toolread3.43.0No change observed
fallow_explainfallow-rs-fallow:tool:fallow_explain
Observed interface and hashes

Explain one fallow issue type without running analysis. Returns the rule id, name, rationale, worked example, fix guidance, and docs URL as JSON. Use this before applying fixes when an agent or reviewer needs to understand what a finding means. If your client exposes MCP resources, `fallow://explain/{issue_type}` serves the same document as a cacheable resource read.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "issue_type": {
      "description": "Issue type or rule id to explain, for example \"unused-export\",\n\"fallow/unused-dependency\", \"high-complexity\", or \"code-duplication\".",
      "type": "string"
    }
  },
  "required": [
    "issue_type"
  ],
  "type": "object"
}
sha256:0515578b0caea2b35ab25ef1db6e1c06d1991da3a0696cc045ff4f0b315aa68c

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:c91a3da85c37ec93371d55d9c18005cc3cd3f9719459c325aad68c640a4b2f4a

Interface hash: sha256:62b1cbafd97ed03ced36be8f604b157d48b6c22ffa977922648922d73ba75243

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/fallow_explain",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "fallow_explain"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:af06b1530648601b979bb9f4e1e834a55975ee05e1c4d22eabba397df6400c95"
}
toolread3.43.0No change observed
feature_flagsfallow-rs-fallow:tool:feature_flags
Observed interface and hashes

Detect feature flag patterns in a TypeScript/JavaScript project. Identifies environment variable flags (process.env.FEATURE_*), SDK calls from common providers, and config object patterns. Returns flag locations, detection confidence, and cross-reference with dead code findings. `retirement: true` adds advisory retirement rows (reasons, git age, evidence).

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "flag_age": {
      "description": "Flag age: \"blame\" (default, lower bound), \"pickaxe\" or \"off\". Needs `retirement`.",
      "type": [
        "string",
        "null"
      ]
    },
    "flag_state": {
      "description": "Offline vendor flag export for the vendor reasons; relative to `root`. Needs `retirement`.",
      "type": [
        "string",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Only analyze production code (excludes tests, stories, dev files).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "retirement": {
      "description": "Add the `retirement` block: one row per flag with reasons, git age and evidence.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "top": {
      "description": "Show only the top N flags.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:4059c30cf8101472daeb009c28860195324053e504aeb9be1e89faf0048bae2b

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:919b45ab996dbbba6df414f75e186aadfbbc763c325406e08afefffc83b82332

Interface hash: sha256:e22646b39e1ab0437f5dbf06c0310fd24a32dbe0c5ff49edf95dbbafc8cd895d

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/feature_flags",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "feature_flags"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:546c9383f7d0065b8ab226d2de8389f32bca183b912b0547da8f3b67527014dc"
}
toolread3.43.0No change observed
find_dupesfallow-rs-fallow:tool:find_dupes
Observed interface and hashes

Find code duplication across the project. Detects clone groups (identical or similar code blocks) with configurable detection modes and thresholds. Returns clone families with refactoring suggestions. On a Rust root, it runs `cargo fallow dupes` (mode, min_tokens, min_lines, threshold). Each clone_groups[] entry carries a stable `fingerprint` (dup:<id>); pass it to the trace_clone tool to deep-dive that group (locations, an extract-function suggestion with estimated savings, and a best-effort suggested name). Set top=N to show only the N highest-ranked clone groups. Ranking combines token count, occurrence count, and a capped spread boost for distant files or same-file locations. Set group_by to "owner" (CODEOWNERS), "directory", "package" (workspace), or "section" (GitLab CODEOWNERS `[Section]` headers, with `owners` metadata per group) to partition results. Import declarations are excluded from clone detection by default (sorted import blocks are a formatting artifact, not copy-paste); pass ignore_imports=false to count them again. Clone instances omit their verbatim `fragment` text over MCP (it was most of the payload, and `file` plus the line/column range addresses the same code); set include_fragments=true to get it back. explain_skipped only changes the human-format skipped-default-ignores note (human/markdown CLI output); MCP JSON responses stay clean. Supports config, workspace scoping, baseline comparisons, and performance tuning (no_cache, threads).

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "baseline": {
      "description": "Compare results against a saved baseline file. Only new clone groups\n(not in the baseline) are reported. The response carries\n`baseline_staleness`: read `gate_trips` to see whether the baseline has\nentries that match nothing any more (re-save it with `save_baseline`),\nand read `change_scoped` first, because a run narrowed to part of the\nproject can report `matched_entries: 0` on a healthy baseline.\n`scope_reasons` names the channels that narrowed it.\n`unrecognised_format: true` means the file is not this command's baseline.\nIt suppressed nothing, so use another path and do not re-save.\n`saved_by` then names the command that wrote it, when fallow knows it.",
      "type": [
        "string",
        "null"
      ]
    },
    "changed_since": {
      "description": "Git ref to compare against when limiting duplication to changed files.",
      "type": [
        "string",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "cross_language": {
      "description": "Enable cross-language detection (strips TypeScript type annotations for TS/JS matching).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "explain_skipped": {
      "description": "Show a per-pattern breakdown for default duplicate ignores. `dupes`\nprints only that breakdown; the built-in discovery ignores are reported\nby `check`, `dead-code`, `audit` and the default run.\nHuman-format only (human/markdown CLI output); MCP JSON responses suppress the note.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "group_by": {
      "description": "Group findings by CODEOWNERS ownership, directory, workspace package, or\nGitLab CODEOWNERS section. Values: \"owner\", \"directory\", \"package\", \"section\".",
      "type": [
        "string",
        "null"
      ]
    },
    "ignore_imports": {
      "description": "Exclude import declarations from clone detection. Defaults to `true`\n(sorted import blocks are a formatting artifact, not copy-paste); set\n`false` to count them again.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "ignore_symlinks": {
      "description": "Omit clone instances whose path is a symlink or lies under a symlinked\ndirectory. Defaults to the project config; set `false` to report them\neven when the config sets `ignoreSymlinks`.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "include_fragments": {
      "description": "Include the verbatim source text on each clone instance. Defaults to\nfalse: `file` plus the line and column range address the same code, and\nthe text is most of the response. Set true only when you need the\nsource without reading the files.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "min_lines": {
      "description": "Minimum line count for a clone. Defaults to the project config, or 5 if unset.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_occurrences": {
      "description": "Minimum number of occurrences before a clone group is reported. Raise\nto focus on widespread copy-paste and skip pair-only clones. Defaults\nto the project config, or 2 if unset.",
      "format": "uint32",
      "minimum": 2,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_tokens": {
      "description": "Minimum token count for a clone. Defaults to the project config, or 50 if unset.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "mode": {
      "description": "Detection mode: \"strict\", \"mild\", \"weak\", or \"semantic\". Defaults to\nthe project config, or \"mild\" if unset.",
      "type": [
        "string",
        "null"
      ]
    },
    "near": {
      "description": "Detect function-scoped near-miss clones in addition to exact clones.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "no_package_baselines": {
      "description": "Ignore the per-package refs of `workspaces.changedSince` for this call,\nso every workspace package is analyzed in full scope. Use it to judge\nor save a whole-project baseline.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "save_baseline": {
      "description": "Save current results as a baseline file for future comparisons. The path\nmust resolve inside the project root, its Git work tree, the CI workspace or a temp directory.\nA relative path resolves against the working directory of the MCP\nserver, not against `root`, so pass an absolute path.",
      "type": [
        "string",
        "null"
      ]
    },
    "skip_local": {
      "description": "Only report cross-directory duplicates.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "threshold": {
      "description": "Fail if duplication exceeds this percentage (0 = no limit). Defaults\nto the project config, or 0 if unset.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "top": {
      "description": "Show only the N highest-ranked clone groups. `clone_families[]` is\nrebuilt from the groups that survive, so it narrows too. `stats` keeps\ndescribing the whole corpus; read `clone_groups_shown` /\n`clone_groups_omitted` and `clone_families_shown` /\n`clone_families_omitted` for the split.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:d5c00cadbb1eea71ebb826127d6f7db31bb5580901ee06a9d708d9cda5509346

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:83691818b1a2812d102cc5af620d87d27feb8b0af0e8d7f03b573cf28e8579ad

Interface hash: sha256:3e4c7fe783314e75858803feb00a4e78f50edf6a657cfe0f86ce97d0713ec5ef

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/find_dupes",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "find_dupes"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:16f2aec49d38e28e4c125973bec7b7e4abbc1ce04a0dc8e8b941c30df388db7f"
}
toolwrite3.43.0No change observed
find_similar_codefallow-rs-fallow:tool:find_similar_code
Observed interface and hashes

Find semantically similar functions with Fallow's exact pinned local model. Results are unverified candidates, not probabilities, duplication findings, refactor instructions, or CI gates. Source stays on the local machine. Each candidate carries stable candidate_id and review_key identities, exact locations, reproducible provider/model provenance, completion accounting, and read-only inspect/review actions. The command never downloads a model: if explicit setup has not happened, it returns structured guidance to run `fallow similar-code setup --local`. Use threshold only as a candidate-retrieval cutoff, then call inspect_similar_code before deciding whether two functions are behaviorally equivalent or safe to consolidate. Supports root, config, workspace, changed_since, changed_workspaces, paths, threshold, min_lines, top, no_cache, and threads. Cold local inference has a dedicated 15-minute subprocess window; FALLOW_TIMEOUT_SECS still overrides it when an operator needs a different bound.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "changed_since": {
      "description": "Git ref used to report candidate pairs touching changed files.",
      "type": [
        "string",
        "null"
      ]
    },
    "changed_workspaces": {
      "description": "Scope candidate reporting to workspaces touched since this git ref.",
      "type": [
        "string",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_lines": {
      "description": "Minimum extracted source lines per function.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "paths": {
      "description": "Report candidate pairs touching one of these project-relative files.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "threshold": {
      "description": "Minimum cosine similarity from zero through one. This is not a\nprobability or verification verdict.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "top": {
      "description": "Cap returned candidates after bounded full-corpus comparison.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to scope candidates to; mutually exclusive with `changed_workspaces`.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:ab56bb116a68ed828693e2219291118ccb6576a48106300c1ce723e290ddb245

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:daa806571a49b509f66d1679487b8ad8463685c1cd7fd6047f1465b9d2de9174

Interface hash: sha256:7b5ee8e0f99dde8d04ab99040988e4763c71a772d5c02f176cd126122c03b6e2

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/find_similar_code",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "find_similar_code"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:173129bfc53f524de5a9dc41224ecf9659c3b4ac11e57599b3ac677de4a55155"
}
toolread3.43.0No change observed
fix_applyfallow-rs-fallow:tool:fix_apply
Observed interface and hashes

Apply auto-fixes to the project. Removes unused exports from the public API, may delete dead exported enum declarations, deletes unused dependencies from package.json, removes unused enum members, removes unused pnpm catalog entries (rewriting empty groups to `{}` so pnpm install does not reject null), and appends duplicate-export `ignoreExports` rules to the fallow config file. When no fallow config exists outside a monorepo subpackage, this CREATES `.fallowrc.json` using `fallow init`'s framework-aware scaffolding (`$schema`, `entry`, `ignorePatterns`, framework defaults) and layers the `ignoreExports` rules on top. Inside a monorepo subpackage (workspace marker `pnpm-workspace.yaml` / `package.json#workspaces` / `turbo.json` / `lerna.json` / `rush.json` above the invocation directory) the create-fallback refuses and emits `skip_reason: "monorepo_subpackage"` with a relative `workspace_root` path; the agent should re-run `fallow init` at the workspace root or invoke from there. Set `no_create_config: true` to opt out of the create-fallback entirely (recommended for CI and unattended use); the duplicate-export path is skipped with `skip_reason: "no_create_config"` and source-file edits proceed normally. When a source file's xxh3 content hash at fix time differs from the hash captured during the in-process analysis (parallel editor save, CI rebase, or other tool mutated the file between analysis and write), the per-file fix is skipped with `skip_reason: "content_changed"`; the envelope's top-level `skipped_content_changed` count is incremented and the run exits with code 2 so CI surfaces the mismatch instead of treating the partial run as a clean no-op. When a source file mixes CRLF and bare-LF line endings, the per-file fix is skipped with `skip_reason: "mixed_line_endings"`; the envelope's top-level `skipped_mixed_line_endings` count is incremented and the run exits with code 2. This skip is NOT self-healing: re-running fallow alone does not normalize the file and will loop. The agent must run `dos2unix <path>` (or instruct the user to set `git config core.autocrlf input` and re-checkout) before re-running. When an unused export lives in a test, mock, or fixture directory (`__mocks__`, `e2e`, `e2e-tests`, `cypress`, `playwright`, `examples`, `fixtures`, `__fixtures__`, `evals`, `golden`), or in a file that itself has an unresolved import, its removal is withheld as low confidence because the consumer may be invisible to static analysis (Vitest mock aliases, off-workspace e2e trees, fixture build steps): the per-file fix carries `skip_reason: "low_confidence_off_graph"` or `"low_confidence_unresolved_imports"` and the envelope's top-level `skipped_low_confidence_exports` count is incremented. A finding carrying `reachability_caveats` (a source file was skipped, unreadable, or unparseable, so the reference that would credit it may never have been seen) is withheld the same way, `remove-dependency`, `remove-enum-member` and `remove-class-member` included, under `skip_reason: "low_confidence_incomplete_analysis"` and the counts `skipped_low_confidence_dependencies` and `skipped_low_confidence_members` (the member count covers both kinds; a class-member removal is only ever opened by the type-aware pass, so only members it had approved can be withheld here); read `workspace_diagnostics[]`, resolve those files, and re-run. Unlike the two skips above these are INTENTIONAL: they do NOT change the exit code, and the finding stays reported by `fallow dead-code` for manual confirmation. Writes are batched: each per-file rewrite is staged to a sibling temp file, and the orchestrator promotes the batch only after every stage succeeds, so a single stage failure leaves the project untouched. Files with a UTF-8 BOM are read with the BOM stripped (so line offsets align with the parser) and written with the BOM re-prepended (so Windows-authored files round-trip unchanged); fallow does not add or remove a BOM. This modifies files on disk. Use fix_preview first to review planned changes including any `proposed_diff` and `created_files` fields. Supports workspace scoping and performance tuning (no_cache, threads).

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "no_create_config": {
      "description": "Refuse to create a new fallow config file when none exists. Use this\nfrom pre-commit hooks and CI bots where silently materializing a new\ntop-level config file would surprise the user.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "show_cascade": {
      "description": "Also fix the unused exports, types, class members and enum members\nof unused files. By default `fix` skips them, as the report hides\nthem. Passed through to the CLI's `--show-cascade` flag.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:26e8666c1dbc4bb5c8ddaa33d690d726d81291c77ae46536121cbe3b8b1e9275

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:c24abc0c89d24fec9d4b27529a52bcb20d19f46d6ed6e711923666799c658fb0

Interface hash: sha256:122c6af677d9560082c251943a1aebcff85556507a54f13874972d88706f8c93

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/fix_apply",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "fix_apply"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:0503514483ba9f64bd330ec25d5cff12fd3a1b814060dcf7df88eaca94126f25"
}
tooldestructive3.43.0No change observed
fix_previewfallow-rs-fallow:tool:fix_preview
Observed interface and hashes

Preview auto-fixes without modifying any files. Shows what would be changed: which unused exports would be removed, which unused dependencies would be deleted from package.json, which unused enum members would be removed, which unused pnpm catalog entries would be cleaned up, and which duplicate-export `ignoreExports` rules would be added to the fallow config file. For `add-to-config` actions, each fix entry carries a `proposed_diff` field with the unified-diff preview of the proposed config write. When no fallow config exists outside a monorepo subpackage, fix_apply would CREATE `.fallowrc.json` using `fallow init`'s framework-aware scaffolding (`$schema`, `entry`, `ignorePatterns`, etc.) and layer the `ignoreExports` rules on top; preview entries on that path carry `created_files: [".fallowrc.json"]`. Set `no_create_config: true` to skip the config-creation path with `skip_reason: "no_create_config"`; source-file previews are unaffected. When a source file's xxh3 content hash at preview time differs from the hash captured during the in-process analysis (a concurrent source edit), the per-file entry is emitted with `skip_reason: "content_changed"` and the envelope's top-level `skipped_content_changed` count is incremented; re-run after refreshing analysis. When a source file mixes CRLF and bare-LF line endings, the per-file entry is emitted with `skip_reason: "mixed_line_endings"` and the envelope's top-level `skipped_mixed_line_endings` count is incremented; this skip is NOT self-healing because re-running fallow alone does not normalize the file. The agent must run `dos2unix <path>` (or instruct the user to set `git config core.autocrlf input` and re-checkout) before re-running. When an unused export lives in a test, mock, or fixture directory, or in a file that itself has an unresolved import, its removal is withheld as low confidence because the consumer may be invisible to static analysis: the per-file entry carries `skip_reason: "low_confidence_off_graph"` or `"low_confidence_unresolved_imports"` and the envelope's top-level `skipped_low_confidence_exports` count is incremented. A finding carrying `reachability_caveats` (a file the run did not fully analyze may hold the crediting reference) is withheld the same way, `remove-dependency`, `remove-enum-member` and `remove-class-member` too, under `skip_reason: "low_confidence_incomplete_analysis"`, counted by `skipped_low_confidence_dependencies` and `skipped_low_confidence_members` (which counts both member kinds). Unlike the two skips above these are INTENTIONAL and do NOT change the exit code; the finding stays reported by `fallow dead-code` for manual confirmation. Supports workspace scoping and performance tuning (no_cache, threads).

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "no_create_config": {
      "description": "Refuse to create a new fallow config file when none exists. Use this\nfrom pre-commit hooks and CI bots where silently materializing a new\ntop-level config file would surprise the user.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "show_cascade": {
      "description": "Also fix the unused exports, types, class members and enum members\nof unused files. By default `fix` skips them, as the report hides\nthem. Passed through to the CLI's `--show-cascade` flag.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:26e8666c1dbc4bb5c8ddaa33d690d726d81291c77ae46536121cbe3b8b1e9275

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:79a433066ed12cf3a7d4eebeebc69bc687c408f6e78df97ed61b3fde695feb67

Interface hash: sha256:261c579b47a7af1a0e2289ee8147827ba42b21dd366b27d265a6cb141001eb9a

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/fix_preview",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "fix_preview"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:8d8b19765b896ca76ab7b8e5cf23846337f022d3569acb34a8f213cd84638afd"
}
toolread3.43.0No change observed
get_blast_radiusfallow-rs-fallow:tool:get_blast_radius
Observed interface and hashes

Return first-class blast-radius context alongside local runtime coverage. Pass `coverage` as a V8 coverage directory, single V8 JSON file, or Istanbul `coverage-final.json`. A single local capture is free and runs without a license; continuous or multi-capture runtime monitoring requires an active license. Returns the standard health JSON; agents should read `runtime_coverage.blast_radius`, which contains stable `fallow:blast:<hash>` IDs, caller counts, traffic-weighted caller reach, and low/medium/high risk bands. This blast-radius signal augments context only: it scores the RISK of changing a function. It MUST NOT gate `safe_to_delete` or a confidence score (a function having callers does not make it 'keep'); only the three-state runtime tracking signal (called / never_called / untracked) can issue a deletion verdict.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "coverage": {
      "description": "Path to runtime coverage input. Accepts a V8 coverage directory\n(`NODE_V8_COVERAGE=<dir>`), a single V8 coverage JSON file, or an\nIstanbul `coverage-final.json`. Required.",
      "type": "string"
    },
    "group_by": {
      "description": "Group health findings by CODEOWNERS ownership, directory, workspace\npackage, or GitLab CODEOWNERS section. Values: \"owner\", \"directory\",\n\"package\", \"section\". `section` attaches an `owners: string[]` array\nto each group. Passed through to the CLI's `--group-by` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "low_traffic_threshold": {
      "description": "Fraction of `trace_count` below which an invoked function is\nclassified `low_traffic` rather than `active`. Expressed as a\ndecimal (0.001 = 0.1%). Inherits the sidecar default (0.001) when\nomitted.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_crap": {
      "description": "Maximum CRAP score threshold (default 30.0). Functions meeting or\nexceeding this score appear as findings alongside complexity violations.\nProduction V8 coverage yields the most accurate per-function CRAP\ninputs, making this flag especially useful on this tool.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_invocations_hot": {
      "description": "Minimum invocation count for a function to be classified as a hot\npath. Inherits the CLI default (100) when omitted.",
      "format": "uint64",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_observation_volume": {
      "description": "Minimum total trace volume before the sidecar may emit high-confidence\n`safe_to_delete` or `review_required` verdicts. Below this threshold,\nconfidence is capped at `medium` to protect against overconfident\nverdicts on new or low-traffic services. Inherits the sidecar default\n(5000) when omitted.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Only analyze production code (excludes tests, stories, dev files).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "top": {
      "description": "Show only the top N runtime findings, hot paths, file scores, and\nrefactoring targets. Passed through to the CLI's `--top` flag.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "coverage"
  ],
  "type": "object"
}
sha256:3215e87877dbee0b159c7091daa9e30465efd53f089ccd1bfc20afe7e475eb62

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:7a9a74bb1ff3d343c68cbe12afb83dcdedfe4bc4a3f521673aaf30d11c765ff2

Interface hash: sha256:b9086414d509ec6806d36fc3d3ee4e0279ae7a9bcd9f9f1edcae21099a141ed6

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/get_blast_radius",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "get_blast_radius"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:b3a808592feb8f7c54085efb3154760e9591c7895c8340eb10851d204c6d2762"
}
toolread3.43.0No change observed
get_cleanup_candidatesfallow-rs-fallow:tool:get_cleanup_candidates
Observed interface and hashes

Return cleanup candidates grounded in local runtime coverage. Pass `coverage` as a V8 coverage directory, single V8 JSON file, or Istanbul `coverage-final.json`. A single local capture is free and runs without a license; continuous or multi-capture runtime monitoring requires an active license. Returns the standard health JSON; agents should read `runtime_coverage.findings` for `safe_to_delete`, `review_required`, `low_traffic`, and `coverage_unavailable` verdicts.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "coverage": {
      "description": "Path to runtime coverage input. Accepts a V8 coverage directory\n(`NODE_V8_COVERAGE=<dir>`), a single V8 coverage JSON file, or an\nIstanbul `coverage-final.json`. Required.",
      "type": "string"
    },
    "group_by": {
      "description": "Group health findings by CODEOWNERS ownership, directory, workspace\npackage, or GitLab CODEOWNERS section. Values: \"owner\", \"directory\",\n\"package\", \"section\". `section` attaches an `owners: string[]` array\nto each group. Passed through to the CLI's `--group-by` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "low_traffic_threshold": {
      "description": "Fraction of `trace_count` below which an invoked function is\nclassified `low_traffic` rather than `active`. Expressed as a\ndecimal (0.001 = 0.1%). Inherits the sidecar default (0.001) when\nomitted.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_crap": {
      "description": "Maximum CRAP score threshold (default 30.0). Functions meeting or\nexceeding this score appear as findings alongside complexity violations.\nProduction V8 coverage yields the most accurate per-function CRAP\ninputs, making this flag especially useful on this tool.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_invocations_hot": {
      "description": "Minimum invocation count for a function to be classified as a hot\npath. Inherits the CLI default (100) when omitted.",
      "format": "uint64",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_observation_volume": {
      "description": "Minimum total trace volume before the sidecar may emit high-confidence\n`safe_to_delete` or `review_required` verdicts. Below this threshold,\nconfidence is capped at `medium` to protect against overconfident\nverdicts on new or low-traffic services. Inherits the sidecar default\n(5000) when omitted.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Only analyze production code (excludes tests, stories, dev files).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "top": {
      "description": "Show only the top N runtime findings, hot paths, file scores, and\nrefactoring targets. Passed through to the CLI's `--top` flag.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "coverage"
  ],
  "type": "object"
}
sha256:3215e87877dbee0b159c7091daa9e30465efd53f089ccd1bfc20afe7e475eb62

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:bd93ed826a2c7605bd14ef21699f7393c3219a1f15ef13b009baec3a7cfed454

Interface hash: sha256:ba3ea2b559f2688a054d2900c17fa667c5fb7baf8b249b74752954c2a1c889d8

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/get_cleanup_candidates",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "get_cleanup_candidates"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:ed90b39b3ec8c163351324c71164cddca7170ec5daca340e208ac8d5ecc400d9"
}
toolread3.43.0No change observed
get_cloud_deployment_changesfallow-rs-fallow:tool:get_cloud_deployment_changes
Observed interface and hashes

Read how production behavior changed between two deployments from Fallow Cloud. Backed by `fallow coverage deployment-changes --format json`. `repo` is required; `sha` defaults to `HEAD` of `root`, `base` to the previous deployment with production runtime. Each function has a change kind (`new_called`, `new_not_called`, `heated_up`, `cooled_down`, `stopped`, `unchanged`); `change`, `limit` and `cursor` filter and page. Read `comparable` first. Context only, never a deletion verdict. Needs `FALLOW_API_KEY` in the server environment.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "base": {
      "description": "Base deployment commit SHA.",
      "type": [
        "string",
        "null"
      ]
    },
    "change": {
      "description": "One change kind to keep.",
      "type": [
        "string",
        "null"
      ]
    },
    "cursor": {
      "description": "`meta.cursor` of the previous page.",
      "type": [
        "string",
        "null"
      ]
    },
    "limit": {
      "description": "Page size, 1 to 200.",
      "format": "uint16",
      "maximum": 65535,
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "repo": {
      "description": "Repository as `owner/repo`. Required.",
      "type": "string"
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "sha": {
      "description": "Deployment commit SHA; defaults to `HEAD`.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "repo"
  ],
  "type": "object"
}
sha256:da2343c012d272b70ddd73843885e2b73c2e5f17ad0b6078cc9d25d5300df9dd

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:86d84cb8e4c11f971cfaed87733d5171919991b159ec02b116fad363d4e045e5

Interface hash: sha256:c5f6499d6f7d2058cfccbb23f92d7aca4f91e9a0ea42d111357c1941e371358b

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/get_cloud_deployment_changes",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "get_cloud_deployment_changes"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:13b06362f1a038c662fd26a51e1cf6ffaf094206fd0c3fda4a0a3759f7382fcf"
}
toolread3.43.0No change observed
get_cloud_review_packetfallow-rs-fallow:tool:get_cloud_review_packet
Observed interface and hashes

Read production facts for a few changed files or functions from Fallow Cloud, with no full pull and no local analysis. Backed by `fallow coverage review-packet --format json`. `repo` is required; pass `files` and/or `functions` (`{file, name, line?}`), or neither to send the files changed against `base`. Rows carry `repo_path`, `tracking_state` (current deployment) and `period_tracking_state` (whole period); `evidence_window` is the real evidence span. A current `never_called` with `period_tracking_state: called` is not dead code. Needs `FALLOW_API_KEY` in the server environment; see `fallow://tools/get_cloud_review_packet`.

Input schema

{
  "$defs": {
    "CloudFunctionTarget": {
      "description": "One function target of `get_cloud_review_packet`.",
      "properties": {
        "file": {
          "description": "Repo-relative file.",
          "type": "string"
        },
        "line": {
          "description": "Start line.",
          "format": "uint32",
          "minimum": 0,
          "type": [
            "integer",
            "null"
          ]
        },
        "name": {
          "description": "Function name.",
          "type": "string"
        }
      },
      "required": [
        "file",
        "name"
      ],
      "type": "object"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "base": {
      "description": "Base ref for the changed-file default.",
      "type": [
        "string",
        "null"
      ]
    },
    "commit_sha": {
      "description": "Deployment commit SHA.",
      "type": [
        "string",
        "null"
      ]
    },
    "files": {
      "description": "Repo-relative files, at most 1000.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "functions": {
      "description": "Functions, at most 1000.",
      "items": {
        "$ref": "#/$defs/CloudFunctionTarget"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "period_days": {
      "description": "Window in days, 1 to 90.",
      "format": "uint16",
      "maximum": 65535,
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "project_id": {
      "description": "Project disambiguator.",
      "type": [
        "string",
        "null"
      ]
    },
    "repo": {
      "description": "Repository as `owner/repo`. Required.",
      "type": "string"
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "repo"
  ],
  "type": "object"
}
sha256:17ad7fc816cde56368e2825f228ae96d691d6e733027a3b72f26cbe2668c47f2

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:79904c6f5865fa9f9cf57bdabcc77e51a8c53f7320cedfa686667ca08e44d0a5

Interface hash: sha256:1bec37480ed5acec2a28f77b7693dc4a995612c8d6d835d9fedbd610c257c647

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/get_cloud_review_packet",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "get_cloud_review_packet"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:4d6e51847c9d59f0b64420d14020c5720808fd43f0c54d3ebef7610315b6a7c5"
}
toolread3.43.0No change observed
get_cloud_runtime_contextfallow-rs-fallow:tool:get_cloud_runtime_context
Observed interface and hashes

Pull runtime coverage for a repository from Fallow Cloud instead of a local V8 or Istanbul dump, and return the same `runtime_coverage` block the local runtime-coverage tools return. Backed by `fallow coverage analyze --cloud --format json`: Fallow Cloud is asked for the repository's runtime facts over the requested window, and the answer is joined against this project's static analysis, so `root` must be a checkout of the same repository. It makes a network call and needs a Fallow Cloud account (for a scoped question, get_cloud_review_packet is smaller); cloud pull is a Team-tier feature, and a repository your org cannot see is refused by the cloud rather than returned empty. The API key is never a parameter: the CLI reads `FALLOW_API_KEY` in the server's own environment, else the key that `fallow cloud login` stored. A call without a key stops before the analysis, with `isError`, `exit_code: 2`, and `code: "cloud_api_key_missing"`. `repo` (`owner/repo`) is required. `project_id`, `period_days` (1-90, default 30), `environment`, and `commit_sha` narrow what the cloud returns; `production`, `top`, and `min_invocations_hot` behave as they do on check_runtime_coverage. Read `runtime_coverage.findings` for `safe_to_delete` / `review_required` / `low_traffic` / `coverage_unavailable` verdicts, `runtime_coverage.hot_paths` for production hot paths, `runtime_coverage.blast_radius` and `runtime_coverage.importance` for review context that never gates a deletion verdict, `runtime_coverage.summary.data_source` to confirm the evidence is `cloud`, and `runtime_coverage.warnings` for the codes that explain a thin answer (`no_runtime_data`, `cloud_functions_unmatched`).

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "commit_sha": {
      "description": "Commit SHA filter for the runtime facts the cloud returns.",
      "type": [
        "string",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "environment": {
      "description": "Runtime environment filter, for example `production`.",
      "type": [
        "string",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_invocations_hot": {
      "description": "Minimum invocation count for a function to be classified as a hot\npath. Inherits the CLI default (100) when omitted.",
      "format": "uint64",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "period_days": {
      "description": "Runtime observation window in days, 1 to 90. Inherits the CLI default\n(30) when omitted.",
      "format": "uint16",
      "maximum": 65535,
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "production": {
      "description": "Only analyze production code (excludes tests, stories, dev files).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "project_id": {
      "description": "Project disambiguator when one repository reports several projects.",
      "type": [
        "string",
        "null"
      ]
    },
    "repo": {
      "description": "Repository Fallow Cloud holds runtime facts for, as `owner/repo`.\nRequired.",
      "type": "string"
    },
    "root": {
      "description": "Project root; defaults to the working directory. It must be a checkout\nof `repo`: cloud functions are joined against its static analysis.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "top": {
      "description": "Show only the top N runtime findings and hot paths.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    }
  },
  "required": [
    "repo"
  ],
  "type": "object"
}
sha256:ee678f3a749450d737f383204ac1ad5aeddb3d756232259a9d5bbc25c36245e9

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:5ec05f7833feafefa3f7154d3f3dfbd05df372b9f12ff954229cde550741c7f7

Interface hash: sha256:42dd7ee55e8e2c23013c0cd03c0b13109870c749e2517c35b46b8988da5b57ef

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/get_cloud_runtime_context",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "get_cloud_runtime_context"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:379720b6ecfa7b3a7feb48147d79c5442d1a1a90c540257d8dbfc9d9c6c4437a"
}
toolread3.43.0No change observed
get_hot_pathsfallow-rs-fallow:tool:get_hot_paths
Observed interface and hashes

Return production hot paths from a local V8 or Istanbul runtime coverage dump. Pass `coverage` as a V8 coverage directory, single V8 JSON file, or Istanbul `coverage-final.json`. A single local capture is free and runs without a license; continuous or multi-capture runtime monitoring requires an active license. Returns the standard health JSON; agents should read `runtime_coverage.hot_paths`, which is sorted by percentile and invocation count. Each entry carries `start_line` and `end_line` so agents can match the function's full body against a PR diff. Use `top` to cap the returned hot paths. Each hot path with a static counterpart also carries `optimization_target`: `cost_score` (invocations multiplied by the per-call cost), `cost_basis` (`inner_iterations` from V8 block counts, else `cognitive`), `cognitive`, `cyclomatic`, `line_count`, and `inner_iterations_per_call`. To pick speed work, sort by `cost_basis` (`inner_iterations` first), then by `cost_score` descending: scores on different bases do not compare. The hot paths are selected and capped by invocations, so a function with fewer calls but more work per call can be absent. Use `get_importance` to judge the risk of a change. Environment-driven scoping: if `FALLOW_DIFF_FILE` (path to a unified diff) is set in the agent's process env, hot paths are narrowed to functions whose `[start_line, end_line]` overlaps an added hunk; a file the diff touched but with no added lines (deletion-only / pure-rename) drops its hot paths rather than falling through to changed-since file-level matching. `FALLOW_CHANGED_SINCE` (git ref) covers the fallback case (file-level match for files NOT in the diff at all). Unset both for project-wide hot paths.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "coverage": {
      "description": "Path to runtime coverage input. Accepts a V8 coverage directory\n(`NODE_V8_COVERAGE=<dir>`), a single V8 coverage JSON file, or an\nIstanbul `coverage-final.json`. Required.",
      "type": "string"
    },
    "group_by": {
      "description": "Group health findings by CODEOWNERS ownership, directory, workspace\npackage, or GitLab CODEOWNERS section. Values: \"owner\", \"directory\",\n\"package\", \"section\". `section` attaches an `owners: string[]` array\nto each group. Passed through to the CLI's `--group-by` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "low_traffic_threshold": {
      "description": "Fraction of `trace_count` below which an invoked function is\nclassified `low_traffic` rather than `active`. Expressed as a\ndecimal (0.001 = 0.1%). Inherits the sidecar default (0.001) when\nomitted.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_crap": {
      "description": "Maximum CRAP score threshold (default 30.0). Functions meeting or\nexceeding this score appear as findings alongside complexity violations.\nProduction V8 coverage yields the most accurate per-function CRAP\ninputs, making this flag especially useful on this tool.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_invocations_hot": {
      "description": "Minimum invocation count for a function to be classified as a hot\npath. Inherits the CLI default (100) when omitted.",
      "format": "uint64",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_observation_volume": {
      "description": "Minimum total trace volume before the sidecar may emit high-confidence\n`safe_to_delete` or `review_required` verdicts. Below this threshold,\nconfidence is capped at `medium` to protect against overconfident\nverdicts on new or low-traffic services. Inherits the sidecar default\n(5000) when omitted.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Only analyze production code (excludes tests, stories, dev files).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "top": {
      "description": "Show only the top N runtime findings, hot paths, file scores, and\nrefactoring targets. Passed through to the CLI's `--top` flag.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "coverage"
  ],
  "type": "object"
}
sha256:3215e87877dbee0b159c7091daa9e30465efd53f089ccd1bfc20afe7e475eb62

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:ecbebe89f29a05e51ab21cfebc72b07f04c492dee151b4062c28516264ddd809

Interface hash: sha256:ba56dc7a68d8b73a29844867d1f62c99c5150858a3dd15cf4ac4dc2df4fc1bc4

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/get_hot_paths",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "get_hot_paths"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:5bb3458d1f1d020da8827c55f7876a118dfcaaa96210ad26c72e2349b3ca69af"
}
toolread3.43.0No change observed
get_importancefallow-rs-fallow:tool:get_importance
Observed interface and hashes

Return first-class production-importance context from local runtime coverage plus static health signals. Pass `coverage` as a V8 coverage directory, single V8 JSON file, or Istanbul `coverage-final.json`. A single local capture is free and runs without a license; continuous or multi-capture runtime monitoring requires an active license. Returns the standard health JSON; agents should read `runtime_coverage.importance`, which contains stable `fallow:importance:<hash>` IDs, invocations, cyclomatic complexity, owner count, a 0-100 score, and a templated reason. This importance signal augments context only. It MUST NOT gate `safe_to_delete` or a confidence score (a high or low score never decides deletion); only the three-state runtime tracking signal (called / never_called / untracked) can issue a deletion verdict.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "coverage": {
      "description": "Path to runtime coverage input. Accepts a V8 coverage directory\n(`NODE_V8_COVERAGE=<dir>`), a single V8 coverage JSON file, or an\nIstanbul `coverage-final.json`. Required.",
      "type": "string"
    },
    "group_by": {
      "description": "Group health findings by CODEOWNERS ownership, directory, workspace\npackage, or GitLab CODEOWNERS section. Values: \"owner\", \"directory\",\n\"package\", \"section\". `section` attaches an `owners: string[]` array\nto each group. Passed through to the CLI's `--group-by` flag.",
      "type": [
        "string",
        "null"
      ]
    },
    "low_traffic_threshold": {
      "description": "Fraction of `trace_count` below which an invoked function is\nclassified `low_traffic` rather than `active`. Expressed as a\ndecimal (0.001 = 0.1%). Inherits the sidecar default (0.001) when\nomitted.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_crap": {
      "description": "Maximum CRAP score threshold (default 30.0). Functions meeting or\nexceeding this score appear as findings alongside complexity violations.\nProduction V8 coverage yields the most accurate per-function CRAP\ninputs, making this flag especially useful on this tool.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_invocations_hot": {
      "description": "Minimum invocation count for a function to be classified as a hot\npath. Inherits the CLI default (100) when omitted.",
      "format": "uint64",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_observation_volume": {
      "description": "Minimum total trace volume before the sidecar may emit high-confidence\n`safe_to_delete` or `review_required` verdicts. Below this threshold,\nconfidence is capped at `medium` to protect against overconfident\nverdicts on new or low-traffic services. Inherits the sidecar default\n(5000) when omitted.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Only analyze production code (excludes tests, stories, dev files).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "top": {
      "description": "Show only the top N runtime findings, hot paths, file scores, and\nrefactoring targets. Passed through to the CLI's `--top` flag.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "coverage"
  ],
  "type": "object"
}
sha256:3215e87877dbee0b159c7091daa9e30465efd53f089ccd1bfc20afe7e475eb62

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:0bc4a964fab605bdab3b22414b8893caed808ee5b8177f619015be48fc4e6651

Interface hash: sha256:9940df77327655aae895789dc680e584855394dccf4f52b40058c7b20085fb9d

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/get_importance",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "get_importance"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:e291c03d6466762cab23eba29050f8c279feb58fc00404ce23fbc15e8f7ef0a9"
}
toolread3.43.0No change observed
get_token_blast_radiusfallow-rs-fallow:tool:get_token_blast_radius
Observed interface and hashes

Return design-token blast radius from static analysis. Runs `fallow health --css --format json`; agents should read `css_analytics.token_consumers`, a reverse index keyed by each token of its defining site plus a `consumer_count` and a capped located `consumers[]` sample of `{path,line,kind}`. Covers TWO token origins, disambiguated by token shape and consumer `kind`: Tailwind v4 `@theme` tokens (`token` is the `--`-prefixed custom property like `--color-brand`; `kind` in `theme-var` / `css-var` / `utility` / `apply`) AND CSS-in-JS token definitions (StyleX `defineVars` / `unstable_defineVarsNested`, vanilla-extract `createTheme` / `createThemeContract` / `createGlobalTheme`; `token` is the binding-qualified dotted access path like `vars.color.primary`, `namespace` is the defining binding, member reads use `js-member`, and StyleX theme-group calls use `js-call`). StyleX theme-group calls credit the complete resolved contract, including partial overrides and empty reset themes. The index is empty or absent on projects using neither. `consumer_count` is a static lower bound because computed class names, dynamic token structures, unresolved imports, and computed token access cannot always be counted. For Tailwind a `consumer_count` of 0 mirrors the unused-theme-token population (the dead-token verdict stays on `unused_theme_tokens` via check_health); CSS-in-JS tokens have no corroborating dead-token finding, so treat a CSS-in-JS 0 as weaker. Use this tool to scope the impact of editing or renaming a token, not to decide deletion.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:fba87f7779d958698322f8f1374284bfeb776972ed2af4e700548e24aa25dea1

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:e31ccaf019707978eaa05fd0db8daf3824702468e557b7afd4d4969d142547b3

Interface hash: sha256:7f11e12335e16299149a3c5289200939d72184c566b9ef1b04b960b07caf05f2

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/get_token_blast_radius",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "get_token_blast_radius"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:031da0596b7284dc14f3f5eae17b9b2e778bcc03a5c46097589ce83f939adf1f"
}
toolread3.43.0No change observed
guardfallow-rs-fallow:tool:guard
Observed interface and hashes

Report the architecture rules that apply to specific files before editing them: the file's boundary zone, which zones it may import from (same-zone imports are always allowed), forbidden call patterns, and every rule-pack policy in scope with its severity and suppression token. Works for files that do not exist yet, so it can be called before writing new code. A path that matches no configured zone returns an empty rule set rather than an error. It reads config only and runs no analysis; to find existing violations use `analyze` or `list_boundaries`.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "files": {
      "description": "Files to report on, project-root-relative. They do not need to exist yet.",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "type": "array"
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "files"
  ],
  "type": "object"
}
sha256:713e1bbb1ad48e0b187e8fea3b2aa7c34684dd10b4a4d64348bb90a05180aede

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:44797d7a3db20b499c6c8c3aa93c2e0ff4b43c46af451a3f106ba06638d28383

Interface hash: sha256:46bccfdff2ae217da533379084c9e00f6047aaa0eb4421959f95e55aa693b18b

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/guard",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "guard"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:51b2c2e6d6dbebfb59b51fea3d074f8295ca2f8fdc5052fde5eaf32decc5d590"
}
toolread3.43.0No change observed
impactfallow-rs-fallow:tool:impact
Observed interface and hashes

Read fallow's local value-tracking report. Runs NO analysis: it reads a per-project history file from the user's private config dir (never inside the repo), answering "what has fallow done for me over time" rather than "what is wrong now" (for live findings use analyze / audit / check_health). LOCAL-DEV ONLY: history accrues only on a developer's machine (local dev, or a persistent pre-commit gate); fallow never records in CI, so in CI / ephemeral runners this returns an empty report (enabled:false) and must NOT be used as a CI metric. Always returns a populated JSON object (never {}): branch on `enabled` and `enabled_source` (`project` = an explicit per-repo enable/disable, `user` = the user-global default, `default` = off). When `enabled:false`, use `explicit_decision` to decide what to say: `explicit_decision:false` means tracking was never set up here, so recommend the user run `fallow impact enable` (do not run it yourself); `explicit_decision:true` means the user deliberately disabled it here, so do NOT nag. Also branch on `record_count` (0 with enabled:true = set up but awaiting gate runs). When enabled with history it returns `surfacing` (issue counts from the most recent recorded run), `trend` (count delta vs the previous run; improving/declining/stable on the wire), `containment_count` + `recent_containment` (pre-commit gate runs that blocked a commit then later cleared), and a short-SHA `latest_git_sha` for correlation. On fallow with impact v1.5+ the report also carries `resolved_total` / `suppressed_total` / `recent_resolved` / `attribution_active`, crediting findings fallow saw genuinely fixed (code removed or refactored) and never counting a fallow-ignore suppression as a win; older fallow binaries omit these fields. On fallow with impact v1.6+ the report also carries `project_surfacing` / `project_trend`: a WHOLE-PROJECT view from the last full `fallow` run (additive optional under the same `schema_version`, omitted by older binaries). Treat changed-file `surfacing` as the actionable count for the current change and `project_surfacing` as whole-repo context, not a to-do list. Read-only; the mutating `fallow impact enable` / `disable` / `default` lifecycle is intentionally not exposed over MCP.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "root": {
      "description": "Project root whose local value history to read (stored outside the repo); defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:947be484e26ba9f3296778b320971c1f4b15ae9c534b1841ec5d73893a1677f7

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:898f1fc495577180b315b8361e14a4551c417b45f12a610245e4a86b76c49365

Interface hash: sha256:5adb20167da7dcad96603d4452607a046e0d9ed33feb934c3a55990cef2b35b9

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/impact",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "impact"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:a1719b3b3b6fcb5fd01422db3e4e8371b78fea8d84bb7a8002830729df48e09f"
}
toolread3.43.0No change observed
impact_allfallow-rs-fallow:tool:impact_all
Observed interface and hashes

Roll EVERY tracked fallow project on this machine into one cross-repo value report (`fallow impact --all --format json`). Runs NO analysis: it reads the per-project history files in the user's private config dir, answering "what has fallow done for me across all my repos". Use this instead of `impact` when the agent wants a portfolio view rather than one repo; use `impact` (with `root`) for a single project. Returns `kind: "impact-cross-repo"` with `schema_version` "2", `project_count` (stores enumerated), `tracked_count` (projects with recorded history shown as rows), `unreadable_count` (corrupt/newer-schema stores skipped), a `totals` roll-up (resolved/contained/surfacing summed over ALL tracked projects, including repos since deleted from disk), and a `projects[]` array. Each project row carries a hashed `project_key` (never a filesystem path, and the only always-present identifier), an optional human `label` (the repo's directory basename; omitted on rows recorded by older fallow binaries, so fall back to `project_key` when `label` is null/absent), `last_recorded`, and a nested per-project `report`. Privacy: the aggregate exposes NO absolute paths, only the hash key plus the basename label. Projects that are enabled but have no recorded history yet are counted in `project_count` but excluded from `projects[]` rows. `sort` orders rows (`recent` default / `resolved` / `contained` / `name`); `limit` caps the rows returned while `totals` still reflect every tracked project. LOCAL-DEV ONLY: history accrues only on developer machines (fallow never records in CI), so in CI / ephemeral runners this returns zero tracked projects and must NOT be used as a CI metric. When `project_count` is 0, no project on this machine has tracking enabled yet: in a local dev session suggest the user run `fallow impact enable` in a repo they care about (do not run it yourself), but in CI stay silent because zero is the expected, non-actionable result. Read-only; the mutating enable / disable / default / reset lifecycle is intentionally not exposed over MCP.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "limit": {
      "description": "Cap the number of project rows returned. Grand totals still reflect\nevery tracked project, including any beyond the cap. Omit for all rows.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "sort": {
      "description": "Row ordering: `recent` (default, most recently recorded project first),\n`resolved` (most findings resolved first), `contained` (most commits\ncontained first), or `name` (alphabetical by project label).",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:411d5e10a77432c23ea92ce06ef1cd3106d38f954573bf07c17ca463dce961a0

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:8f1ad89ca961a76d9e3eb758bc79092954a1280be64bb6686846641ad09acaad

Interface hash: sha256:9283fdf1900ffc4276b078619a13ca105e7129a37207a2509569555f3c3d2d2e

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/impact_all",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "impact_all"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:eeb020d47e4acb409640da4fc2a6082052ac405f6fbd617ba429a0e08bc315e3"
}
toolread3.43.0No change observed
impact_closurefallow-rs-fallow:tool:impact_closure
Observed interface and hashes

Trace a file's impact closure. Runs `fallow dead-code --impact-closure <path> --format json --quiet` and returns the transitive affected-but-not-in-diff set plus coordination gaps for file-contract consumers. Evidence for review planning, not proof that affected files are wrong. Gaps carry `search_visibility`; see fallow://tools/impact_closure. Supports root, config, production, workspace, no_cache, and threads.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "path": {
      "description": "Project-relative path to the file whose impact closure to trace.",
      "minLength": 1,
      "type": "string"
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "path"
  ],
  "type": "object"
}
sha256:661e505bba8edafa06011b5d94949464b57b65910f0a1117028eabc40f039222

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:b9c93a2cb5850a90d01fae8c181e6b6d6981e5f8fa7f11e63253c11a351ad302

Interface hash: sha256:d678a9d15ef0ace55627d9c695c05addbb0379c5fa74f5881aadb94ca1f49099

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/impact_closure",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "impact_closure"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:58cab1c02f05078b1eb1636f910ff3a275ef4e0da08035fc4348c927963a1a75"
}
toolread3.43.0No change observed
inspect_similar_codefallow-rs-fallow:tool:inspect_similar_code
Observed interface and hashes

Inspect one exact unverified candidate from find_similar_code without rerunning provider retrieval or global ranking. Pass candidate_id plus a bounded snapshot containing the unchanged discovery schema_version, generation, selected candidate, completion, and diagnostics fields. Current source is re-extracted and both source_sha256 values must still match before bounded source windows, syntactic behavior hints, graph relationships, reachability, callers/callees, ownership, churn, tests, and deterministic clone overlap are returned. Stale source fails closed. Missing evidence is represented explicitly, never inferred. This remains read-only and never declares behavioral equivalence or refactor safety.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "candidate_id": {
      "description": "Snapshot-stable candidate identity returned by `find_similar_code`.",
      "type": "string"
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "snapshot": {
      "additionalProperties": true,
      "description": "Bounded exact-candidate snapshot object selected from the original\ndiscovery response. Pass generation, candidate, completion, and\ndiagnostics unchanged; inspect validates current source hashes before\nenrichment. Read `fallow://schema/similar-code-snapshot` for the full\nobject shape; a snapshot that does not match it is refused with\n`FALLOW_MCP_INVALID_CANDIDATE_SNAPSHOT`.\n\nDeserialized as an untyped `Value` because the shape check lives in the\nhandler, but published with the `object` constraint it always had:\nunconstrained, a client-side validator would accept a string or a\nnumber here and only the server would say no.",
      "type": "object"
    }
  },
  "required": [
    "candidate_id",
    "snapshot"
  ],
  "type": "object"
}
sha256:4e109a283884d38500074ac1c73b44849e23253849d3c7d95a1b6fd0ce05cda6

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:4a592a42d6ecb2c835402559146f714d82165261940c0ed434b5c6de6411b428

Interface hash: sha256:00a010d5654ba73cea58ce996cbac866d9a5ec311b9ff4e84eb1c698efdee0d0

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/inspect_similar_code",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "inspect_similar_code"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:658f834915c326ae261be6455552305cd811bb7965495186cab7dff9783d29c0"
}
toolread3.43.0No change observed
inspect_targetfallow-rs-fallow:tool:inspect_target
Observed interface and hashes

Inspect one file or exported symbol and return one typed evidence bundle. Address a file with target={type:"file", file:"src/a.ts"}; address a symbol with target={type:"symbol", file:"src/a.ts", export_name:"foo"}. Composes existing read-only analysis systems only: trace_file, trace_export for symbols, file-scoped dead-code actions, duplication groups filtered to the file, complexity findings filtered to the file, security candidates scoped to the file, and the impact closure for the file (the transitive affected-but-not-in-diff set plus the coordination gap: modules that consume this file's contract but are not shown alongside it; a syntactic attention pointer, not a correctness proof). Set include_churn=true to attach target-level git churn from the in-process health hotspot subsystem; it is off by default, and missing git history is reported explicitly. Set cloud=true on a file target to attach the `cloud` evidence section of `fallow inspect --cloud` (Fallow Cloud production data per local function); repo selects the `owner/repo`. The key comes from the server environment or `fallow cloud login`, never from the call. The section status is ok, no_key, plan_required, unavailable, or untracked, and a status other than ok does not fail the call; see fallow://tools/inspect_target. Set format="compact" to get the plain text of `fallow inspect --format compact` (about 1 KB, no JSON) instead of the bundle. production is forwarded only to child analyses that support it: trace, dead-code, and health. Symbol targets include file-scoped evidence with explicit scope fields because file:line enclosing-symbol mapping is a follow-up. This bundled query runs independent evidence analyses in parallel; large repositories can exceed the default 120s subprocess timeout, so raise FALLOW_TIMEOUT_SECS when needed.

Input schema

{
  "$defs": {
    "InspectFormatParam": {
      "description": "Response format of the `inspect_target` tool.",
      "oneOf": [
        {
          "const": "json",
          "description": "The JSON evidence bundle.",
          "type": "string"
        },
        {
          "const": "compact",
          "description": "The plain text of `fallow inspect --format compact`.",
          "type": "string"
        }
      ]
    },
    "InspectTarget": {
      "oneOf": [
        {
          "properties": {
            "file": {
              "minLength": 1,
              "type": "string"
            },
            "type": {
              "const": "file",
              "type": "string"
            }
          },
          "required": [
            "type",
            "file"
          ],
          "type": "object"
        },
        {
          "properties": {
            "export_name": {
              "minLength": 1,
              "type": "string"
            },
            "file": {
              "minLength": 1,
              "type": "string"
            },
            "type": {
              "const": "symbol",
              "type": "string"
            }
          },
          "required": [
            "type",
            "file",
            "export_name"
          ],
          "type": "object"
        }
      ]
    },
    "TypeAwareRequireParam": {
      "enum": [
        "best-effort",
        "complete"
      ],
      "type": "string"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "cloud": {
      "description": "OPT-IN (default off): attach the Fallow Cloud `cloud` evidence section\nfor a FILE target: production data per local function. The CLI reads\nthe key: `FALLOW_API_KEY` in the server environment, else the key that\n`fallow cloud login` stored. The section `status` is `ok`, `no_key`,\n`plan_required`, `unavailable` or `untracked`. A status other than `ok`\ndoes not fail the call. Refused for a symbol target.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "format": {
      "anyOf": [
        {
          "$ref": "#/$defs/InspectFormatParam"
        },
        {
          "type": "null"
        }
      ],
      "description": "Response format: `json` (default) returns the evidence bundle.\n`compact` returns the plain text of `fallow inspect --format compact`:\nabout 1 KB, one line per item, and no JSON."
    },
    "include_churn": {
      "description": "OPT-IN (default off): attach target-level git churn evidence. Missing\ngit history is returned as an explicit unavailable evidence section.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies. Forwarded only to child\nanalyses that support it: trace, dead-code, and health.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "repo": {
      "description": "Fallow Cloud repository for `cloud`, as `owner/repo`. Needs\n`cloud: true`. Precedence: this value, then `FALLOW_REPO` in the server\nenvironment, then the `origin` git remote.",
      "type": [
        "string",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "symbol_chain": {
      "description": "OPT-IN (default off): also attach the best-effort symbol-level call chain\n(`fallow trace`) as the `symbol_chain` evidence section. Only\nmeaningful for a SYMBOL target. Best-effort, syntactic (ADR-001), and\nEXPLICITLY OFF the ranked path: resolved-vs-unresolved callees are\nreported honestly, the chain is never folded into the ranked brief and is\nnever a focus-map / ranking input.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "target": {
      "$ref": "#/$defs/InspectTarget",
      "description": "The file or exported symbol to inspect. See the tool description for\nthe two addressing shapes."
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "type_aware": {
      "description": "Include project-wide TypeScript semantic evidence for symbol targets.\n`false` keeps the run syntactic, also when the config turns type-aware analysis on. `type_aware_projects` or `type_aware_require` turns it on and wins over `false`.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "type_aware_projects": {
      "description": "Explicit tsconfig paths for type-aware analysis.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "type_aware_require": {
      "anyOf": [
        {
          "$ref": "#/$defs/TypeAwareRequireParam"
        },
        {
          "type": "null"
        }
      ],
      "description": "Whether incomplete semantic evidence is advisory or gating."
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "target"
  ],
  "type": "object"
}
sha256:20e0d3a4d49ebcb3a1ab9ea00456d3e5087d3c50cdcf0482c9b5350dd548ad6d

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:589ba957514e05d2a5df9a4e2393dd77f37f068b870c96d91e520d3d65ac7407

Interface hash: sha256:6b2303b1672ad34b58b91d7b1bbc00b42b156fc952c16e1b80bdeca67b376449

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/inspect_target",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "inspect_target"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:62823f9b428246a08f7073939f11ac73819a9a1b17b03df9bfd14a7e2ddc0bfb"
}
toolread3.43.0No change observed
list_boundariesfallow-rs-fallow:tool:list_boundaries
Observed interface and hashes

List architecture boundary zones and access rules configured for the project. Returns zone definitions (name, glob patterns, matched file count), access rules (which zones may import from which), and `logical_groups[]` (one entry per pre-expansion `autoDiscover` zone, surfacing the user-authored parent name, verbatim `auto_discover` paths, discovered `children`, `status` (`ok` / `empty` / `invalid_path`), `source_zone_index`, summed `file_count`, optional `authored_rule`, optional `fallback_zone` cross-reference for the Bulletproof case, optional `merged_from` when the parent name was declared multiple times, optional `original_zone_root` echo for monorepo subtree scopes, and optional `child_source_indices` attribution when multiple paths were authored). If boundaries are not configured, returns {"configured": false}; in that case, boundary violation checks will find no issues and can be skipped. Use this to understand the project's architecture constraints before running analysis.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:b1527fa2a26c431dd8554176731439e5c1e8292ae1c8f7ffc617e6311b7544c9

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:fbd29f60a1db4c6c09bbb453da057b7a0b9690131d59801ba5036ca18bdc807a

Interface hash: sha256:cf186f6095fb7114f4fdcbf4d19e63614ce7c2520dac9be097d76cce463cd403

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/list_boundaries",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "list_boundaries"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:f9e86f12d303a3dd29bed4b2c3994960426cf3ef60685c990076110d3ad735b7"
}
toolread3.43.0No change observed
list_suppressionsfallow-rs-fallow:tool:list_suppressions
Observed interface and hashes

List active fallow-ignore suppression markers grouped per file with line, kind, level, reason, and a stale cross-reference. Runs `fallow suppressions --format json` and returns the `kind: "suppression-inventory"` envelope verbatim (a `summary` roll-up plus `files[]`); a governance surface for distrusting a clean verdict by seeing what is suppressed, not a gate, so it always exits 0 even when suppressions exist. Scope with `workspace`, `changed_since` (the natural pull-request review scope), or repeated `file` entries. Read-only. It runs a full analysis to populate the inventory, so on large repos raise `FALLOW_TIMEOUT_SECS` above the default 120s if it times out.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "changed_since": {
      "description": "Git ref (e.g. \"main\", \"HEAD~5\"). Scopes the inventory to files changed\nsince the ref, the natural pull-request review scope.",
      "type": [
        "string",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "file": {
      "description": "Only list suppressions in these files. Relative paths resolve against the\nproject root; forwarded as a repeated `--file` flag.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Only analyze production code (excludes tests, stories, dev files).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:085efb51b787e3a4b2d2566c7abd843b3408f7f01d2e8d7d8e96c6214c488a12

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:a67eb632812b15df90d107119646ad278a7d19bc2c7e6efd5a03f8cada9b4da2

Interface hash: sha256:854f115aede74a4218b716b94fc773928882fc92d660cce7677798d71b3bc9a4

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/list_suppressions",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "list_suppressions"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:9aede2c076658ac2d2d00b5f1a68b89b8f0e0d362ba7eb096a62e46e35a9a533"
}
toolread3.43.0No change observed
mutation_inspectfallow-rs-fallow:tool:mutation_inspect
Observed interface and hashes

Inspect one mutant of a saved `fallow mutation` JSON report (default: the report that the last run saved in the Fallow cache): original and mutated code, covering tests, and the killing test. A source_sha256 mismatch with the current file gives a stale status, not a wrong answer. This tool never runs tests. A report needs the CLI command `fallow mutation`, which executes the project's tests, so ask your host first. On a Rust root, it reads only the cached map of `cargo fallow mutants`.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Used only\nwithout `report`, as for `config`. Defaults to false and never grants\nprocess-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file. Used only without `report`, to find the\ncache directory that holds the report of the last run.",
      "type": [
        "string",
        "null"
      ]
    },
    "mutant_id": {
      "description": "The `mutant_id` from a mutation plan or report.",
      "minLength": 1,
      "type": "string"
    },
    "package": {
      "description": "The Cargo package of a Rust workspace with more than one package.\nValid only on a Rust workspace.",
      "type": [
        "string",
        "null"
      ]
    },
    "report": {
      "description": "Path to a saved `fallow mutation` report or `mutation_plan` output.\nA relative path resolves against `root`. Without `root`, it resolves\nagainst the working directory of the MCP server. Omitted: the report\nthat the last `fallow mutation` run saved in the Fallow cache of the\nproject.",
      "minLength": 1,
      "type": [
        "string",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "mutant_id"
  ],
  "type": "object"
}
sha256:5348d88a04cd0752a33eea3eeab82e44b60f3311e1735a10dd3dbd32f28ed5d2

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:c63af23379c1839b71fc4c626b5c499d629c23e668bfbcf0b7dd0a64666b7917

Interface hash: sha256:ee3f5c6c22775060b0f7995d9018445f5cea58bb6ddc4a244d43fc546f426346

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/mutation_inspect",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "mutation_inspect"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:8f5f88d6f11809a014b474de21d8ebf541cb201a10e17d35f21e8aef337d3a0d"
}
toolread3.43.0No change observed
mutation_planfallow-rs-fallow:tool:mutation_plan
Observed interface and hashes

Plan mutation testing and return the plan envelope: each mutant's id, position, operator, disposition, and static test files, plus a source_sha256 per file. Scope: changed code by default, or `all`, or `paths`. This tool never runs tests. Running the mutants needs the CLI command `fallow mutation`, which executes the project's tests, so ask your host first. On a Rust root, it runs `cargo fallow mutants --list` for one `package`, by default all of it.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "all": {
      "description": "Plan every source file instead of the changed code.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "changed_since": {
      "description": "Base ref for the default changed-code scope. Omitted: the base is\ndetected as for `audit`.",
      "type": [
        "string",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "function_scope": {
      "description": "Plan every mutant of each function that holds a changed line. Omitted:\nthe `mutation.functionScope` config key, else the changed lines only.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "max_mutants": {
      "description": "Maximum number of mutants to plan; the rest are `pending`. A run fills\nthe limit with covered mutants, so it can also run a `pending` one.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "mutants_per_line": {
      "description": "Keep at most this many mutants on each line; the rest are `pending`\nwith the reason `sampled-out`. Omitted: the `mutation.mutantsPerLine`\nconfig key, else no limit.",
      "format": "uint",
      "minimum": 1,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "operators": {
      "description": "Kebab-case operator names, for example `relational-operator`.\nOmitted: the `mutation.operators` config key, else the default set.\nThe opt-in operators, such as `block-statement`, run only when named.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "package": {
      "description": "The Cargo package of a Rust workspace with more than one package.\nValid only on a Rust workspace, where the plan covers the whole package\nunless `paths` or `changed_since` is set.",
      "type": [
        "string",
        "null"
      ]
    },
    "paths": {
      "description": "Plan only these files or directories, relative to the root.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:acb23b3579b5c196434e9cf76a4fff8c6882ac6111b0311e57eeece146994e32

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:87be6cc9564a898483b1bdba153ab3cea0efe05973d08cb5f5577429978d9d49

Interface hash: sha256:3a43f77177064080350afb75d754851a5b8ffdba1e159cad0afbdbdd258730cd

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/mutation_plan",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "mutation_plan"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:c09f2167d4d64faa386598a9decc63033aa2d1d0fa3c3f2b7df2c9c896189f15"
}
toolread3.43.0No change observed
mutation_tasksfallow-rs-fallow:tool:mutation_tasks
Observed interface and hashes

List the open tasks of a saved `fallow mutation` JSON report as one batch (default: the report that the last run saved in the Fallow cache). A task is a survived or no_coverage mutant: a small change to the code that no test detected. Each task has the mutant_id, file, line, function, operator, status, the source lines before and after the change (original_lines, mutated_lines), and the covering test files. After `fallow mutation --record-args values`, a task can have witness; only witness.verdict witness gives a test input (args, original, mutant), and a verdict is never equivalent; see fallow://tools/mutation_tasks. Write tests that pass on the current code and fail on the changed code; one test can cover several tasks, and a task that no input can detect can be skipped. A task whose file changed after the report is stale and has no code. This tool never runs tests. A report needs the CLI command `fallow mutation`, which executes the project's tests, so ask your host first. A Rust root is not supported yet.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Used only\nwithout `report`, as for `config`. Defaults to false and never grants\nprocess-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file. Used only without `report`, to find the\ncache directory that holds the report of the last run.",
      "type": [
        "string",
        "null"
      ]
    },
    "report": {
      "description": "Path to a saved `fallow mutation --format json` report. A relative\npath resolves against `root`. Without `root`, it resolves against the\nworking directory of the MCP server. Omitted: the report that the last\n`fallow mutation` run saved in the Fallow cache of the project.",
      "minLength": 1,
      "type": [
        "string",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:8a0915b038ea57871c1e4bf8c537db0b5248fe420917e9259fca2dbdae5ddff6

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:a063744fde71483012ad8ab1f7b3296e87dc5f83e20280d4c12a5886bf19a1aa

Interface hash: sha256:65b5b60e3bfcfd65ebab1e80b854b59e72933b8f5ec952d38331ad204f39e7e1

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/mutation_tasks",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "mutation_tasks"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:1a11b15879562d00396b36eb11ebf3df9567eed238deb335917218d1f6cbff5a"
}
toolread3.43.0No change observed
project_infofallow-rs-fallow:tool:project_info
Observed interface and hashes

Get project metadata: active framework plugins, discovered source files, and detected entry points. Useful for understanding how fallow sees the project before running analysis. Supports performance tuning (no_cache, threads).

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "boundaries": {
      "description": "Include discovered architecture boundary zones in the response.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "entry_points": {
      "description": "Include entry-point patterns in the response.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "files": {
      "description": "Include discovered source files in the response.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "plugins": {
      "description": "Include active framework plugins in the response.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:2f1173e499409c68d9960bc7e17a0362601e5fedbd03ac203f505d7b4f6c740a

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:43a54b5b5df5ba122c44ecdb4fb03fb41b6aecb8570cbfa71ebd4153be7678e5

Interface hash: sha256:a18e66504d89131cddee5b8a426f57c85ca7976d39f1ad3c1eafe74e09560fa0

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/project_info",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "project_info"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:9ba50a3cb10b4e1618c0117296364da810858787425caf9d1b1f2d0b7546ea9f"
}
toolread3.43.0No change observed
recommendfallow-rs-fallow:tool:recommend
Observed interface and hashes

Recommend a project-tailored fallow config for an agent to author (`fallow recommend --format json`). Read-only: runs project detection (frameworks, workspace layout, tooling) but NOT the analysis pipeline, and always exits 0. Returns `{detected, proposed_config, decisions[]}`. `detected` is what fallow saw; `proposed_config` is a safe starting config that BOTH validates against config-schema AND loads through fallow's real config loader; `decisions[]` is THREE-valued: `auto` (decided from unambiguous detection and applied silently), `default` (a disclosed, overridable default carrying a quantified `rationale`), and `taste` (a genuinely subjective choice surfaced as an open, AskUserQuestion-shaped `question` with 2-4 options and NO baked-in recommended answer, per fallow's taste-ownership principle). Framework rules are never uniformly auto-enabled on a heterogeneous monorepo; entry points beyond the obvious fall back to fallow's own defaults rather than a baked-in guess. Zero-config is a valid stop: the proposed config is an optional refinement over already-strong defaults, not a requirement. Pair with `fallow schema` (the capability manifest carrying per-rule default severity + opt-in) for the full cold-start discover -> recommend -> ask-taste -> author sequence. Honors `root`.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "root": {
      "description": "Project root for framework, workspace, and tooling detection; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:c017ea53cbb8eb5b19675b62d760378a4373d39d5d02005155821333de3a96dd

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:4cbf287814ad3a49c5245aaf5c4aa619289848cf1c4f363023a49b946aad1d60

Interface hash: sha256:a4e1febe4330e1e4fa5adadfaeb464da6ed7026b3946dd6f12d820ac1a2a732e

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/recommend",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "recommend"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:6449055255833e77a962c03f421b782ceecaea8e2a4f2c5d6405e86c4003d361"
}
toolread3.43.0No change observed
security_candidatesfallow-rs-fallow:tool:security_candidates
Observed interface and hashes

Returns unverified security candidates, not confirmed vulnerabilities. Runs `fallow security --format json` and returns `kind: "security"`, `security_findings`, category, CWE, severity, evidence, structural trace, reachability ranking context, blind-spot counters, and optional unresolved-callee diagnostics for agent verification. `severity` is a review-priority tier, not a verified vulnerability verdict. Each finding also carries an agent-actionable `candidate` record (`source_kind`, the untrusted-input kind as a stable catalogue id or null; a self-contained `sink` with the captured callee and optional `url_shape` for URL candidates; and the `boundary` crossed), an optional `taint_flow` source-to-sink triple (present only when an untrusted source is import-reachable to the sink), a `finding_id` (the SARIF fingerprint), and a `stable_finding_id` that survives line moves, for verdicts. Set `surface: true` to include the top-level `attack_surface` inventory with source-to-sink paths and defensive-boundary verification prompts. Set gate to `new` for changed-line candidates or `newly-reachable` for candidates that became reachable from entry points; `newly-reachable` requires changed_since. There is no `impact` field: deciding exploitability is the agent's job. `reachability.untrusted_source_trace` is module-level context only and does not prove value flow. `reachability.taint_confidence` tiers reachable candidates as `arg-level` or `module-level`; tier from that field rather than evidence prose. Verify trace, reachability context, severity, and evidence before editing code or presenting a finding as a vulnerability. Supports root, config, workspace, changed_since, paths, changed_workspaces, surface, gate, no_cache, and threads. Use paths for the agent edit loop: it forwards to `fallow security --file` and scopes returned candidates to matching finding anchors, trace hops, untrusted-source reachability trace hops, or unresolved-callee diagnostics while cached analysis keeps reruns fast. The CLI also honors `FALLOW_DIFF_FILE` from the MCP server environment for line-level diff scoping. Security analysis can exceed the default 120s subprocess timeout on large repos; raise `FALLOW_TIMEOUT_SECS` accordingly.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "changed_since": {
      "description": "Git ref to compare against when limiting candidates to changed files.",
      "type": [
        "string",
        "null"
      ]
    },
    "changed_workspaces": {
      "description": "Scope candidates to workspaces touched since this git ref. Mutually\nexclusive with `workspace`.",
      "type": [
        "string",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "gate": {
      "description": "Optional security regression gate. Valid values: \"new\" or\n\"newly-reachable\". The \"newly-reachable\" gate requires `changed_since`.",
      "type": [
        "string",
        "null"
      ]
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "paths": {
      "description": "Scope candidates to just-edited files for the agent edit loop. Each path\nis passed to `fallow security --file` and matches finding anchors or\ntrace hops.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "surface": {
      "description": "Include the attack-surface inventory with defensive-boundary verification\nprompts in the JSON response.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to scope candidates to; mutually exclusive with `changed_workspaces`.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:bb739bc3ff24c2922fff689c72203868cc1b5f76dfbfd8ba539003c3b3a68a56

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:15c62c5e15e2ffba3f361fdeba7002cd4346d5104edd3a1d0934e839f1ff5d71

Interface hash: sha256:8951b1f8d31614bcd435986b3e137ce2b4681b262d8b5625bd0f43da48311253

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/security_candidates",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "security_candidates"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:5995ad470197d4c12ecb3faf2dfb0040f9fdf75b9c96d13240848a53217378bd"
}
toolread3.43.0No change observed
symbol_impactfallow-rs-fallow:tool:symbol_impact
Observed interface and hashes

Return exact-symbol consumers, transitive affected files, and targeted tests for a TypeScript export or exported class method. Select either export_name, or both class_name and member_name. The result is advisory project-impact evidence and does not duplicate tsc or Oxlint diagnostics.

Input schema

{
  "$defs": {
    "TypeAwareRequireParam": {
      "enum": [
        "best-effort",
        "complete"
      ],
      "type": "string"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false,
  "oneOf": [
    {
      "not": {
        "anyOf": [
          {
            "required": [
              "class_name"
            ]
          },
          {
            "required": [
              "member_name"
            ]
          }
        ]
      },
      "required": [
        "export_name"
      ]
    },
    {
      "not": {
        "required": [
          "export_name"
        ]
      },
      "required": [
        "class_name",
        "member_name"
      ]
    }
  ],
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "class_name": {
      "description": "Exact exported class name. Must be paired with `member_name`.",
      "minLength": 1,
      "type": [
        "string",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "export_name": {
      "description": "Exact exported symbol name. Mutually exclusive with the class-method\nselector.",
      "minLength": 1,
      "type": [
        "string",
        "null"
      ]
    },
    "file": {
      "description": "Project-root-relative declaration file.",
      "minLength": 1,
      "type": "string"
    },
    "member_name": {
      "description": "Exact method name. Must be paired with `class_name`.",
      "minLength": 1,
      "type": [
        "string",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "type_aware_projects": {
      "description": "Explicit tsconfig paths. Project auto-discovery is used when omitted.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "type_aware_require": {
      "anyOf": [
        {
          "$ref": "#/$defs/TypeAwareRequireParam"
        },
        {
          "type": "null"
        }
      ],
      "description": "Whether incomplete semantic evidence is advisory or gating."
    }
  },
  "required": [
    "file"
  ],
  "type": "object"
}
sha256:80522a89f654b29e2a85c86f4f57bfffcf383e4afbef261b558b9331220125bb

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:dec5f199f75ab741a44b4bff6657aef77fc5e5f45e9a03c20f5599bd759c82be

Interface hash: sha256:c8c02ac53f35a9ffc99ba589f98a9eb452bb0b481c2a04b33105720ba70c0e7e

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/symbol_impact",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "symbol_impact"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:4718380ea3ad9f4d6df60f4e1c935b2bc8079308907da2af1a995f507c6b0d94"
}
toolread3.43.0No change observed
trace_clonefallow-rs-fallow:tool:trace_clone
Observed interface and hashes

Deep-dive a duplicate-code clone group. Address it either by a source location (file + line) or by a stable fingerprint (fingerprint="dup:<id>" from a find_dupes clone_groups[].fingerprint, usually dup:<8hex> and widened only on rare report collisions). Returns the matched clone instance, every sibling clone group / location, plus per group an extract-function suggestion with estimated line savings and a best-effort suggested_name (the field is omitted, not null, when there is no confident name, so branch on key presence; advisory, verify before applying, never auto-apply). Provide exactly one addressing form. Import declarations are excluded from clone detection by default; pass ignore_imports=false to count them again. Use after find_dupes when consolidating duplication and you need exact sibling locations and a refactor target.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "cross_language": {
      "description": "Enable cross-language detection (strips TypeScript type annotations for TS/JS matching).",
      "type": [
        "boolean",
        "null"
      ]
    },
    "file": {
      "default": null,
      "description": "Project-relative path to a file containing the clone instance. Used\nwith `line` to address by source location; omit when using `fingerprint`.",
      "type": [
        "string",
        "null"
      ]
    },
    "fingerprint": {
      "default": null,
      "description": "Stable clone-group identity (`dup:<id>`) from a `find_dupes`\n`clone_groups[].fingerprint`. Alternative to addressing by `file` plus `line`.",
      "type": [
        "string",
        "null"
      ]
    },
    "ignore_imports": {
      "description": "Exclude import declarations from clone detection. Defaults to `true`\n(sorted import blocks are a formatting artifact, not copy-paste); set\n`false` to count them again.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "ignore_symlinks": {
      "description": "Omit clone instances whose path is a symlink or lies under a symlinked\ndirectory. Defaults to the project config; set `false` to report them\neven when the config sets `ignoreSymlinks`.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "line": {
      "default": null,
      "description": "Line number of the clone instance within `file`. Used with `file` to\naddress by source location; omit when using `fingerprint`.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_lines": {
      "description": "Minimum line count for a clone. Defaults to the project config, or 5 if unset.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_occurrences": {
      "description": "Minimum number of occurrences before a clone group is reported.\nDefaults to the project config, or 2 if unset.",
      "format": "uint32",
      "minimum": 2,
      "type": [
        "integer",
        "null"
      ]
    },
    "min_tokens": {
      "description": "Minimum token count for a clone. Defaults to the project config, or 50 if unset.",
      "format": "uint32",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "mode": {
      "description": "Detection mode: \"strict\", \"mild\", \"weak\", or \"semantic\". Defaults to\nthe project config, or \"mild\" if unset.",
      "type": [
        "string",
        "null"
      ]
    },
    "near": {
      "description": "Detect function-scoped near-miss clones before resolving the trace.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "skip_local": {
      "description": "Only report cross-directory duplicates.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "threshold": {
      "description": "Fail if duplication exceeds this percentage (0 = no limit). Defaults\nto the project config, or 0 if unset.",
      "format": "double",
      "type": [
        "number",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "type": "object"
}
sha256:809919972f174ee8a1b1386198ac1e7dc260a7f81ce1e257a3eb94c51a854891

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:bbf1805ec855d7b7920ea6d787f25ec496469f9dbc93fdf2d04a6bf3333f6a49

Interface hash: sha256:fadab0a28a07f5704ac6765dfbe32ae64794b71bcd09917955e5861831583e52

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/trace_clone",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "trace_clone"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:a8c8a160fd232abeaf626f9776244528b6a8a6dab1ae295b24ad78f60e719360"
}
toolread3.43.0No change observed
trace_dependencyfallow-rs-fallow:tool:trace_dependency
Observed interface and hashes

Trace where a dependency is used. Returns which files import the package, which imports are type-only, whether the package is referenced from package.json scripts or CI configs (`used_in_scripts`), and whether the dependency is used at all (`is_used` accounts for imports, script usage, and the used packages that list it as a peer (`peer_of`), matching the unused-deps detector). `unused_in` names each manifest that the detector still flags, because an import credits only the nearest manifest that installs the package. Set `usage`, `specifiers`, `sites` (paged with `limit` and `cursor`) or `closure_depth` to add a `usage` object: per imported name, the file, call and unresolved counts, one hop through project wrappers, and the usage sites. Useful before removing a dependency, moving it between dependencies and devDependencies, or migrating its API.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "closure_depth": {
      "description": "Add importers of the users, up to this depth. Implies `usage`.",
      "format": "uint32",
      "maximum": 10,
      "minimum": 1,
      "type": [
        "integer",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "cursor": {
      "description": "`usage.sites.next_cursor` of the previous page.",
      "type": [
        "string",
        "null"
      ]
    },
    "limit": {
      "description": "Sites per page (default 50). Implies `sites`.",
      "format": "uint16",
      "maximum": 500,
      "minimum": 1,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "package_name": {
      "description": "Name of the npm package to trace usage for.",
      "minLength": 1,
      "type": "string"
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "sites": {
      "description": "Add one page of usage sites. Implies `usage`.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "specifiers": {
      "description": "Imported names to report. Implies `sites`.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "usage": {
      "description": "Add the per-name `usage` counts.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "package_name"
  ],
  "type": "object"
}
sha256:7e1c6bb50acb8abd75c69180286d989a9fbb60dc94db6064f03f9993fc857722

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:8f4f07c15fa952c177deca7fce766b5ff8f711499fcf074620f6cc722dba4d95

Interface hash: sha256:e2db89ac9b736051c4ae352eafd4c9656b95b67ea70ae2501b65cf30d7740f51

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/trace_dependency",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "trace_dependency"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:7cc33f793791bb7cd001c217b37af280800c9d0294918d4e2876e3068b377ad9"
}
toolread3.43.0No change observed
trace_errorfallow-rs-fallow:tool:trace_error
Observed interface and hashes

Resolve a runtime stack trace against the project graph: paste the trace text in `trace` and get, per frame, which definitions in THIS project the frame's identifier names. The verb for "my service threw this in production, what code is that". Returns `kind: "trace-error"` with retained frames in input order, each carrying an `origin` (`in_project`, `node_modules`, `out_of_corpus`) and a `resolution` (`resolved`, `ambiguous`, `not_found`, `not_attempted`), plus `candidates[]` naming the file, symbol, member and declaration line. It is built to refuse overclaiming: a frame matching several definitions is `ambiguous`, with bounded candidates and `candidates_omitted` instead of a preferred match, a frame the graph was never asked about is `not_attempted` rather than a softer `not_found`, and `line_mismatch` marks a resolved frame whose own line sits at a different declaration, so a name-only match is visible instead of implied. `counts` closes over the reported frames and publishes `frames_omitted` and `unparsed_lines`, so a capped or unreadable input cannot look complete. No source maps are read: a frame inside built output says so instead of being rebound through a map that may be stale, so give it a trace from unbundled source or the source paths a map already resolved. The RESOLUTION outcome never fails the call: a trace in which nothing resolves is an ANSWER, and exits 0. A refused input still is a refusal: an empty or oversized `trace` returns `isError` with `FALLOW_INVALID_TRACE_OPTIONS`.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "source": {
      "description": "Where the trace came from, echoed back as the payload's `source`.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "trace": {
      "description": "The runtime stack trace text, pasted verbatim.",
      "minLength": 1,
      "type": "string"
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "trace"
  ],
  "type": "object"
}
sha256:b110ff15953b0eb5bae8ba835c66fec66284b4ec0ebcc80eef811c66943997ce

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:117f413b8ac6bd8fa5f62c3ea0e3f57b80463d6793ac2225c24c943a2dcc2243

Interface hash: sha256:f95bb905223f980b147a72b8943e074cf2e0dbab5182eb3c198b5c9c4166d86a

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/trace_error",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "trace_error"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:912a280c224abb5878c4ea2b8c2b2f5cd2532453ec1fc2b3d97153748e6b6ed9"
}
toolread3.43.0No change observed
trace_exportfallow-rs-fallow:tool:trace_export
Observed interface and hashes

Trace why an export is considered used or unused. Returns file reachability, entry-point status, direct references, re-export chains, the framework plugin rules that mark the export as used (`plugin_credits`), and a concise reason string. If export_name is a class / enum / store MEMBER rather than a top-level export, returns a member trace instead (carrying member_name, member_kind, owner_export, owner_is_used) that reports the owning class's reachability and usage plus a pointer to the matching --unused-<kind>-members command, so a class-member finding can be debugged too. Use this when an agent needs evidence before deleting or rewriting a supposedly unused export or class member. References carry `search_visibility`; see fallow://tools/trace_export. When the config or FALLOW_TYPE_AWARE turns type-aware analysis on, the trace also carries a `semantic` block with checker-backed evidence, as `fallow dead-code --trace` does.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "export_name": {
      "description": "Name of the exported symbol (or class/enum/store member) to trace.",
      "minLength": 1,
      "type": "string"
    },
    "file": {
      "description": "Project-relative path to the file that declares the export.",
      "minLength": 1,
      "type": "string"
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "file",
    "export_name"
  ],
  "type": "object"
}
sha256:2b3608246bee54562cc79c7c327fb302da2941fd2714018d0664608985fd99f7

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:b6509adc9eda702cf3689ace3c878b15f523069a08c85c15e26d6b04be9125da

Interface hash: sha256:9b61e5428ec131e274ebe658d90edd12cf53807fddb0462f80f61c475038150d

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/trace_export",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "trace_export"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:22e31f229cbf5878e363149bb23617c49adfd82a02a0fd5e23a6d2260d650883"
}
toolread3.43.0No change observed
trace_filefallow-rs-fallow:tool:trace_file
Observed interface and hashes

Trace a file's graph context. Returns whether the file is reachable or an entry point, what it exports, what it imports, what imports it, and which re-exports it declares. Use this to understand whether a file is isolated, barrel-only, or imported by live entry points.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "file": {
      "description": "Project-relative path to the file to trace.",
      "minLength": 1,
      "type": "string"
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "file"
  ],
  "type": "object"
}
sha256:a023d41ae271ced1c5f9275717c3d4e9937d11b6614407e4e5cc2281530c2392

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:ca363b359316b88c2e7ecd8c8368e9415287a1054c13fa8f01a2e0658615bab6

Interface hash: sha256:318228e9a957cbda736cf17ec06a5b4396784eca32039e79ed7fc5d917acd0fe

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/trace_file",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "trace_file"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:d7e221845a030daff8c8745f7afc890e8e7a41dd5b3ee93b7a6abdf1e155471a"
}
toolread3.43.0No change observed
trace_import_pathfallow-rs-fallow:tool:trace_import_path
Observed interface and hashes

Shortest import path from one module to another, hop by hop with each hop's import line and whether the hop is type-only. Unreachable answers `reachable: false`; the same module answers `reachable: true`. Both report `hops: 0`, so branch on `reachable`, not the count. Exact project paths take priority; ambiguous abbreviations are refused. Use trace_file for one file's direct neighbours.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "from": {
      "description": "Project-relative path of the module the walk starts from.",
      "minLength": 1,
      "type": "string"
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "production": {
      "description": "Production mode: exclude test, story, and dev files, only start/build\nscripts, and report type-only dependencies.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "to": {
      "description": "Project-relative path of the module the walk is looking for.",
      "minLength": 1,
      "type": "string"
    },
    "workspace": {
      "description": "Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.",
      "type": [
        "string",
        "null"
      ]
    }
  },
  "required": [
    "from",
    "to"
  ],
  "type": "object"
}
sha256:d312729297052de81fc6b6e0b7d884f93f0c8e22cfa45c59f9ac95115de732e8

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:11ee6e774267c0cbaaa5bbec97f7199ff8114dc7e8d2ef7b65ad2219d758c2d9

Interface hash: sha256:9eb4c39c48406fb5dd0befe1f0bb499ae70a0679310aff9b5cb2d17c5280d847

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/trace_import_path",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "trace_import_path"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:d178f8bb863c1a7b3cd73739ffed3748d2068c834b0215b4be5321008febbcd1"
}
toolread3.43.0No change observed
trace_symbolfallow-rs-fallow:tool:trace_symbol
Observed interface and hashes

Trace an exact TypeScript symbol with checker-backed references, namespace identity, aliases, and re-export hops. Root trace fields preserve syntactic context; treat `semantic.references`, `semantic.status`, and `semantic.identity` as the authoritative exact evidence. The proof covers only the lane named by `semantic.target.namespace`, so a root trace that lists a reference the proof does not is wider evidence rather than stale. This is project-wide evidence for Fallow decisions, not a compiler-diagnostic or lint-rule surface.

Input schema

{
  "$defs": {
    "TypeAwareRequireParam": {
      "enum": [
        "best-effort",
        "complete"
      ],
      "type": "string"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "allow_remote_extends": {
      "description": "Allow trusted HTTPS config `extends` for this request. Defaults to false\nand never grants process-global trust.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "config": {
      "description": "Path to a fallow config file.",
      "type": [
        "string",
        "null"
      ]
    },
    "export_name": {
      "description": "Name of the exported symbol to trace.",
      "minLength": 1,
      "type": "string"
    },
    "file": {
      "description": "Project-relative path to the file that declares the export.",
      "minLength": 1,
      "type": "string"
    },
    "max_output_bytes": {
      "description": "Byte cap for this call's response. Lowers the server cap (default\n1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "no_cache": {
      "description": "Disable the incremental parse cache.",
      "type": [
        "boolean",
        "null"
      ]
    },
    "root": {
      "description": "Project root; defaults to the working directory.",
      "type": [
        "string",
        "null"
      ]
    },
    "threads": {
      "description": "Parser thread count; defaults to CPU cores.",
      "format": "uint",
      "minimum": 0,
      "type": [
        "integer",
        "null"
      ]
    },
    "type_aware_projects": {
      "description": "Explicit tsconfig paths. Project auto-discovery is used when omitted.",
      "items": {
        "type": "string"
      },
      "type": [
        "array",
        "null"
      ]
    },
    "type_aware_require": {
      "anyOf": [
        {
          "$ref": "#/$defs/TypeAwareRequireParam"
        },
        {
          "type": "null"
        }
      ],
      "description": "Whether incomplete semantic evidence is advisory or gating."
    }
  },
  "required": [
    "file",
    "export_name"
  ],
  "type": "object"
}
sha256:26e9b38211f9406964efed5887a59614d580f35c7193b22ad408cd28723c141b

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:3bd99fa1bed374d3afe7f1efc6fdd93a0db344c2bf81bcc19741cf08ff80977a

Interface hash: sha256:9940caf7b2cc2a3ee95088ffb8a1f6180b8d1a2c7042805c5e5395e1e10c9512

Other observed Modelara metadata
{
  "id": "mcp:fallow-mcp/trace_symbol",
  "source": {
    "type": "mcp",
    "server": "fallow-mcp",
    "operation": "trace_symbol"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:2a0e70f1aa7df1768007050df269e66be03a1c6d2e486792890e7e71e42b8bad"
}
toolread3.43.0No change observed

STATIC COMPARISONS

Release history

2 release transitions
  1. 0 added0 removed0 schema0 write0 destructive0 unknown

    Nov 16, 2026· Automated static analysis

  2. 0 added0 removed0 schema0 write0 destructive0 unknown

    Nov 16, 2026· Automated static analysis