Developer-tools MCP server

Docmancer

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

View watchlist

DistributionDistribution: PyPI
Packagedocmancer
Latest analyzed version0.9.17
Current tool count20
Latest analysisNov 16, 2026
Package source

OBSERVED INTERFACE

Capability surface

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

3 releases analyzed0.9.15 → 0.9.17Latest: 0.9.17
  • read12
  • write5
  • destructive3
  • 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
docmancer@0.9.17
Registry
pypi
Published
Aug 13, 2026
Integrity
sha256-/FaHDDcA8y3J1ISHIvYze6XEjS4u6tezMN0JOdbkM1w=
Analyzer
modelara v0.1.8 · policy not recorded
Repository
https://github.com/docmancer/docmancer

20 capabilities

CapabilityTypeDerived effectFirst observed in Valyd coverageLast changed
ask_memorydocmancer:tool:ask_memory
Observed interface and hashes

READ-ONLY: recall one bounded bundle of everything local memory knows about a task, combining mandatory policy, curated memory, and supporting harvested agent evidence in priority order. This is the default recall tool and the right first call when you do not already know which store holds the answer; search_memory and search_evidence each cover only one store. Local and free by default. Returns an empty bundle rather than an error when nothing relevant exists, so an empty result means the memory is genuinely silent. Parameters: task is the natural-language task or question to recall for; answer defaults to false and returns the raw bundle, and setting it true spends a configured provider call, which may leave the machine, to produce a grounded cited answer; mode sets that answer's verbosity to concise, normal, or thorough and is ignored when answer is false; token_budget bounds the bundle size in approximate tokens (default 4000); limit caps how many supporting evidence items are considered (default 12); include_history adds superseded evidence; agent is the requesting agent identifier recorded for attribution (default mcp-client); project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns an object with the mandatory policy, curated memory, and evidence sections, each carrying source citations, plus the generated answer when answer is true.

Input schema

{
  "properties": {
    "agent": {
      "default": "mcp-client",
      "description": "Target agent identifier used to shape and attribute the result. Defaults are tool-specific.",
      "title": "Agent",
      "type": "string"
    },
    "answer": {
      "default": false,
      "description": "When true, spend a configured provider call to generate a grounded cited answer from the recalled memory instead of returning the bundle alone.",
      "title": "Answer",
      "type": "boolean"
    },
    "include_history": {
      "default": false,
      "description": "When true, include historical or superseded memory evidence in addition to active evidence.",
      "title": "Include History",
      "type": "boolean"
    },
    "limit": {
      "default": 12,
      "description": "Maximum number of matching results to return. Defaults are tool-specific.",
      "title": "Limit",
      "type": "integer"
    },
    "mode": {
      "default": "normal",
      "description": "Answer verbosity when answer is true. Ignored when answer is false. Defaults to normal.",
      "enum": [
        "concise",
        "normal",
        "thorough"
      ],
      "title": "Mode",
      "type": "string"
    },
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    },
    "task": {
      "description": "Natural-language task or question to recall relevant policy, memory, and evidence for.",
      "title": "Task",
      "type": "string"
    },
    "token_budget": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Approximate maximum token size of the returned bundle. Omit to use the tool default.",
      "title": "Token Budget"
    }
  },
  "required": [
    "task"
  ],
  "title": "ask_memory_toolArguments",
  "type": "object"
}
sha256:9941bb1c8f5560062bdff9e3ac96176ab3b1b1ca25e5518194f85ea8dc2f3017

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:37990882c6776aa3f7b96e0de1f7103252c7bbda3198bcb5a4c4ec4f11918c9c

Interface hash: sha256:bff7bb6da246ad07040db241d380a4e0c603360eb68abc673c18ad93554979c3

Other observed Modelara metadata
{
  "id": "mcp:docmancer/ask_memory",
  "title": "Recall memory for a task",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "ask_memory"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:e24210324abf30828cbbb8137ca43f0b0614efc80593e5446fc29ce9d22737ee"
}
toolread0.9.150.9.16
canonical_memorydocmancer:tool:canonical_memory
Observed interface and hashes

READ-ONLY: read the machine-wide canonical memory, which is what docmancer has reconciled about this user across every agent and project. Local disk read, machine-wide, so it takes no project_path. Call it before asking the user something they may already have told another agent. Not a search tool: it returns whole prepared sections rather than matches, so use search_memory or ask_memory to look something up. To change what it returns, use pin_memory rather than edit_memory. Parameters: section selects one of about (who the user is), preferences (how they want to work), working-principles (cross-project rules), active-projects (what they are working on), or canonical-memory (a description of the store itself); omit section entirely for a status summary of every section. Returns, with a section, that section split into its pinned zone (durable, survives reconciliation) and its generated zone (rewritten automatically), plus content_hash and revision id. Without a section, returns per-section presence and pinned-line counts.

Input schema

{
  "properties": {
    "section": {
      "anyOf": [
        {
          "enum": [
            "about",
            "preferences",
            "working-principles",
            "active-projects",
            "canonical-memory"
          ],
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Canonical section to read. Omit for a status summary of every section.",
      "title": "Section"
    }
  },
  "title": "canonical_memoryArguments",
  "type": "object"
}
sha256:838b7c4525fe15c519f5b7e139c06385a3d70dfa7a5a1088291b13e20d5f3b4c

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:ea463e15d63fd549119e358bdf2705c0d30d12760ad2cc04c74ff2402af92bc3

Interface hash: sha256:f50d76fbecbc94b4e3e800cea978c20f9e01a4f521aee269e52d8acc63d8184a

Other observed Modelara metadata
{
  "id": "mcp:docmancer/canonical_memory",
  "title": "Read canonical memory about the user",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "canonical_memory"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:0e02624113ff47e605ac27e08a46a36f96201c17bd1f8ee8e6aca528859ac9e3"
}
toolread0.9.150.9.16
common_memorydocmancer:tool:common_memory
Observed interface and hashes

READ-ONLY: list the memories that recur across two or more independent agent harnesses. This is a local disk read over already-harvested evidence; docmancer's own generated integration copies are excluded so they cannot manufacture agreement. Recurrence is evidence of salience, not proof of correctness, so treat the result as a signal worth checking rather than settled truth. Takes no query: it returns the whole recurring set. Use search_evidence to look something specific up instead. Parameters: project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns a list of objects describing each recurring memory and the harnesses it was seen in. Returns [] when nothing recurs.

Input schema

{
  "properties": {
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    }
  },
  "title": "common_memoryArguments",
  "type": "object"
}
sha256:8e147a1b6f9b9ba0f83fd2f428f0e944452053abc33a9106137b19f24feff516

Output schema

{
  "properties": {
    "result": {
      "anyOf": [
        {
          "items": {
            "additionalProperties": true,
            "type": "object"
          },
          "type": "array"
        },
        {
          "additionalProperties": true,
          "type": "object"
        }
      ],
      "title": "Result"
    }
  },
  "required": [
    "result"
  ],
  "title": "common_memoryOutput",
  "type": "object"
}
sha256:8841f249a701b52df1e00129927db4fb9e94a7e6d0381ba0499a494749a4e25e

Description hash: sha256:27b6f87b8cab86bac37249024fbf30c06bc7cef6cdb9a969f8441aedce5253ed

Interface hash: sha256:8321b54fd21c918ff1c11c26ff842c60db9421059b6e83184677b7df6b96967f

Other observed Modelara metadata
{
  "id": "mcp:docmancer/common_memory",
  "title": "Memories recurring across agents",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "common_memory"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:66335b08a0e369d8e871bf809b9f6ba5772ff4bad8560d26386df88f716f6f80"
}
toolread0.9.150.9.16
context_deliverydocmancer:tool:context_delivery
Observed interface and hashes

READ-ONLY: show, per agent, whether context is actually reaching it, listing each supported agent's integration mode, hook installation status, and the revision and hash of the last context bundle it was observed to receive. Local disk read with no side effects. This is the delivery question, so use it to diagnose why one agent seems to be missing context that another has. It is one of three context tools: context_status answers what the current context revision contains and how fresh it is, and context_projection renders the actual text one agent would receive. Read-only across all three; installing hooks and refreshing context are deliberately human-only CLI or local-web operations. Parameters: project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns a list with one row per agent giving its integration mode, hook status, and last delivered revision and hash. A stale or absent revision on one row is the signal to look for.

Input schema

{
  "properties": {
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    }
  },
  "title": "context_deliveryArguments",
  "type": "object"
}
sha256:8d23484b3dbf06faf6fa71f8e7c188fa4c57c9ab8113f93adaaef3316ed64f2a

Output schema

{
  "properties": {
    "result": {
      "anyOf": [
        {
          "items": {
            "additionalProperties": true,
            "type": "object"
          },
          "type": "array"
        },
        {
          "additionalProperties": true,
          "type": "object"
        }
      ],
      "title": "Result"
    }
  },
  "required": [
    "result"
  ],
  "title": "context_deliveryOutput",
  "type": "object"
}
sha256:3753053c51cb6bf8240d98be9a676669b73c3156f6b7b820105cd219a5ac5ae4

Description hash: sha256:228eb48e6ba1fc2f9fd456ce97c28ff241be46bf21fdda2be1d4e4894ae382d4

Interface hash: sha256:49767b0585e59aa5cbd3fb09cff82d72af8f261e21172e23996b4fd202aa6fc1

Other observed Modelara metadata
{
  "id": "mcp:docmancer/context_delivery",
  "title": "Per-agent context delivery status",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "context_delivery"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:c84d86477e34c8970e12b530186825a6ef65f85ba977248abf36ea1680e17029"
}
toolread0.9.150.9.16
context_projectiondocmancer:tool:context_projection
Observed interface and hashes

READ-ONLY: render the actual bounded context text one named agent would receive, linked to the current revision. Local disk read that renders without writing, refreshing, or delivering anything, so it is safe to preview repeatedly. This is the show-me-the-content question, so use it to check what an agent will actually see before installing or debugging an integration. It is one of three context tools: context_status reports the revision and its freshness, and context_delivery reports whether each agent is receiving it. Refresh, rollback, adopt, and retire are human-only CLI or local-web operations. Parameters: agent is the required target agent identifier, and the projection is shaped for that agent's integration; token_budget bounds the rendered size in approximate tokens (default 2000), so raising it returns more content and lowering it truncates by priority; project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns an object with the rendered projection text and the revision it was built from.

Input schema

{
  "properties": {
    "agent": {
      "description": "Target agent identifier used to shape and attribute the result. Defaults are tool-specific.",
      "title": "Agent",
      "type": "string"
    },
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    },
    "token_budget": {
      "default": 2000,
      "description": "Approximate maximum token size of the returned context projection.",
      "title": "Token Budget",
      "type": "integer"
    }
  },
  "required": [
    "agent"
  ],
  "title": "context_projectionArguments",
  "type": "object"
}
sha256:a39f94591c123e6a758a5fa7674aa3085bacc9fb96ddd76172c654df877f28b4

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:983516774f924af6815e254e8b7924796d563bb212d991f1eceb43a0eadcc5ec

Interface hash: sha256:a5b37942c601a4c5819df46ca0112a6c57b376afcc388c97c8d2f24a03442900

Other observed Modelara metadata
{
  "id": "mcp:docmancer/context_projection",
  "title": "Render a context projection for an agent",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "context_projection"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:f4e32f3e5128a18f5e8ad831e55623899ce10dc262f7f6b15a5d2f9e9ab657da"
}
toolread0.9.150.9.16
context_statusdocmancer:tool:context_status
Observed interface and hashes

READ-ONLY: inspect the consolidated Context itself, reporting its current revision id, how fresh it is, which sources are excluded, and its cluster metadata. Local disk read with no side effects. This is the what-and-how-fresh question, so use it to decide whether the context an agent is working from is stale or is missing something on purpose. It is one of three context tools: context_delivery answers whether each agent is actually receiving it, and context_projection renders the actual text one agent would receive. Refresh, rollback, adopt, and retire are deliberately human-only CLI or local-web operations, so no MCP tool can change what this reports. Parameters: project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns an object with the current revision, its scope and freshness, the active exclusions, and cluster metadata.

Input schema

{
  "properties": {
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    }
  },
  "title": "context_statusArguments",
  "type": "object"
}
sha256:db308f58ce83dbd7d43d9624dbb367f8ebc1e14aeb9876bcb7e81fe1a7f0d8c2

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:9f6e95a95349c54ab3528a17707612f46b3d68fd944dbfdba4a87431f45f2f52

Interface hash: sha256:8ac1e096cd3ee3a6a2fde536b45d7584549c7f60db54004c2e876eab8b3e2a0d

Other observed Modelara metadata
{
  "id": "mcp:docmancer/context_status",
  "title": "Consolidated context revision status",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "context_status"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:2af775fc4fe97f04e563eb598718eecaa3765b2ffe5d9f94fd5c79230f69fb07"
}
toolread0.9.150.9.16
decision_timelinedocmancer:tool:decision_timeline
Observed interface and hashes

READ-ONLY: show the append-only history of how memory changed over time, with a human-readable diff per entry. Local disk read over a log that is only ever appended to, so nothing here can be rewritten and the record is trustworthy. Use it to answer when and how a memory changed, or to recover text that an edit replaced. Newest entries come first. This is history, not content: use search_memory or read_memory for what a file says now. Parameters: file_id restricts the timeline to one memory file's own history, which is the usual way to trace a single decision; operation restricts it to one kind of change, one of create, edit, move, duplicate, trash, restore, pin, or reconcile; limit caps how many entries come back (default 100); project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Omit every filter for the whole recent history. Returns a list of entries with the operation, timestamp, affected file, revision ids, and a readable diff.

Input schema

{
  "properties": {
    "file_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Stable memory file identifier. Supply it to restrict the timeline to one file's history.",
      "title": "File Id"
    },
    "limit": {
      "default": 100,
      "description": "Maximum number of matching results to return. Defaults are tool-specific.",
      "title": "Limit",
      "type": "integer"
    },
    "operation": {
      "anyOf": [
        {
          "enum": [
            "create",
            "edit",
            "move",
            "duplicate",
            "trash",
            "restore",
            "pin",
            "reconcile"
          ],
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Operation name used to restrict the timeline to one kind of change. Omit for every operation.",
      "title": "Operation"
    },
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    }
  },
  "title": "decision_timelineArguments",
  "type": "object"
}
sha256:fba385e282396d609bf5126e37c1d5795649372e9b8813be1d6d517b74f584b0

Output schema

{
  "properties": {
    "result": {
      "anyOf": [
        {
          "items": {
            "additionalProperties": true,
            "type": "object"
          },
          "type": "array"
        },
        {
          "additionalProperties": true,
          "type": "object"
        }
      ],
      "title": "Result"
    }
  },
  "required": [
    "result"
  ],
  "title": "decision_timelineOutput",
  "type": "object"
}
sha256:0d4278519fef586eb49e608a7fa626d779b322d128e5f71de3aedc3effcacb02

Description hash: sha256:d1271e037aa1ef74d3edf08147f66b943d0c703542b1394be86eda353eb6dc47

Interface hash: sha256:5dc2944ffb25784f07b391b61b5c9bc1b6cacd576e43298991d484eb3a18416d

Other observed Modelara metadata
{
  "id": "mcp:docmancer/decision_timeline",
  "title": "Memory change timeline",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "decision_timeline"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:8bb90442d7edd8f1f1a2e579f68a63a7eb257f7cbedfde79a5850e02acf5c804"
}
toolread0.9.150.9.16
duplicate_memorydocmancer:tool:duplicate_memory
Observed interface and hashes

MUTATING: copy one curated memory file to a new path under a new stable identity. Writes to local disk and appends to the change timeline. The original is left untouched, and the copy gets its own docmancer://memory address and its own history, so the two diverge from here and editing one does not affect the other. Use it to fork an existing memory into a variant. Use move_memory instead when the original should not survive. Not idempotent: calling it twice with the same new_relative_path fails on the second call rather than creating a second copy. Parameters: address identifies the file to copy; new_relative_path is the copy's path in the tree, including the .md suffix, and must not already exist; expected_hash is the source file's current content_hash from read_memory, which guards against copying a revision you have not seen; project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns an object with the new copy's address, path, content_hash, and revision id.

Input schema

{
  "properties": {
    "address": {
      "description": "Stable docmancer://memory/<id> address, relative path, or exact title of the memory file.",
      "title": "Address",
      "type": "string"
    },
    "expected_hash": {
      "description": "The file's current content_hash from a prior read_memory call. A stale value fails safely instead of overwriting a newer revision.",
      "title": "Expected Hash",
      "type": "string"
    },
    "new_relative_path": {
      "description": "Relative path, including the .md suffix, for the memory file inside its selected memory tree.",
      "title": "New Relative Path",
      "type": "string"
    },
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    }
  },
  "required": [
    "address",
    "new_relative_path",
    "expected_hash"
  ],
  "title": "duplicate_memoryArguments",
  "type": "object"
}
sha256:4153ffe8bff2827c8f2aa7818e7336ab16eeb35aada4533c02539ba933a6c47b

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:e253f8e9aa68ea9e54393b0ab320aa0ef0642f722cc62702b6303efb7d6934f5

Interface hash: sha256:1e6ac6d8d5e631e53354dbf2b6f32019995d47b5de04a72aaf4f9dd201ae0867

Other observed Modelara metadata
{
  "id": "mcp:docmancer/duplicate_memory",
  "title": "Duplicate a memory file",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "duplicate_memory"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:b01a92b896a5567b5e0c853f4f30d29d7b3a5137e5dbc5c65e3174094c25a1e8"
}
toolwrite0.9.150.9.16
edit_memorydocmancer:tool:edit_memory
Observed interface and hashes

MUTATING: replace the body of one existing curated memory file while preserving its frontmatter, address, and history. Writes to local disk and appends to the change timeline. The write is guarded: a stale expected_hash fails without changing anything and returns a structured error naming the re-read-and-retry next action, so concurrent edits cannot be lost. Read the file first to obtain the hash. Not for canonical memory about the user, which reconciliation regenerates: use pin_memory there. Not for creating a new file: use write_memory. Parameters: address identifies the file to edit; text is the complete replacement Markdown body, which overwrites rather than appends; expected_hash is the content_hash from the read that produced text; project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns an object with the address and the new content_hash and revision id.

Input schema

{
  "properties": {
    "address": {
      "description": "Stable docmancer://memory/<id> address, relative path, or exact title of the memory file.",
      "title": "Address",
      "type": "string"
    },
    "expected_hash": {
      "description": "The file's current content_hash from a prior read_memory call. A stale value fails safely instead of overwriting a newer revision.",
      "title": "Expected Hash",
      "type": "string"
    },
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    },
    "text": {
      "description": "Markdown body to write or replace. Replaces the body wholesale; it is not appended.",
      "title": "Text",
      "type": "string"
    }
  },
  "required": [
    "address",
    "text",
    "expected_hash"
  ],
  "title": "edit_memoryArguments",
  "type": "object"
}
sha256:49e1802b41e9e6243697884defa338c12ac02d0d8fd3af77006f187387956147

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:98bd43737512f49519b5a243ff5cb3890d3835d8c45935eaa1740ecd086c8558

Interface hash: sha256:53959ba524ca1b3633e64cc2186803c47779d7d901d34566dca8120863db2053

Other observed Modelara metadata
{
  "id": "mcp:docmancer/edit_memory",
  "title": "Replace a memory file body",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "edit_memory"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:3f9168bcb384c614a046e758afaa250d2bac8bcec2b9f6ac4116446551e00a9e"
}
toolwrite0.9.150.9.16
evidence_statusdocmancer:tool:evidence_status
Observed interface and hashes

READ-ONLY: report whether the local evidence index that search_evidence queries is present and populated, including its on-disk path and its source and section counts. Local only, and takes no parameters. Call it first when search_evidence returns nothing, to tell an empty index apart from a genuine miss; an empty one means the user has not run `docmancer setup` yet. Not for curated memory health, which is context_status, nor for per-agent delivery, which is context_delivery. Returns an object with the index path and the number of indexed sources and sections.

Input schema

{
  "properties": {},
  "title": "evidence_statusArguments",
  "type": "object"
}
sha256:ad4cdab07ecbfba231120cbfd1d76c757555931c7b38e92127cf04bcc8e9f1b9

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:2ebf5cb0d5d6f90374c7dae8ef420e33584adfce6bb34b2379683f43398fbaf5

Interface hash: sha256:53ca9a8da6c8e1b20c81bf0e84023f5b28b032d5c219c2f186bb8764d75a5c23

Other observed Modelara metadata
{
  "id": "mcp:docmancer/evidence_status",
  "title": "Evidence index status",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "evidence_status"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:08837ff9064adf403f700a4b03d41e2810b64e640fcd6f552071bebc120e7310"
}
toolread0.9.15No change observed
move_memorydocmancer:tool:move_memory
Observed interface and hashes

MUTATING and DESTRUCTIVE at the old path: move or rename one curated memory file. Writes to local disk and appends to the change timeline. The file's stable docmancer://memory address survives the move, so existing references by address keep working, but the old relative path stops resolving and anything referring to it by path breaks. Guarded by expected_hash, so a stale hash fails without changing anything. The body is untouched: use edit_memory to change content, or duplicate_memory to copy rather than move. Parameters: address identifies the file to move; new_relative_path is its destination path in the tree, including the .md suffix, and renaming is just a move within the same directory; expected_hash is the file's current content_hash from read_memory; project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns an object with the unchanged address, the new path, and the new revision id.

Input schema

{
  "properties": {
    "address": {
      "description": "Stable docmancer://memory/<id> address, relative path, or exact title of the memory file.",
      "title": "Address",
      "type": "string"
    },
    "expected_hash": {
      "description": "The file's current content_hash from a prior read_memory call. A stale value fails safely instead of overwriting a newer revision.",
      "title": "Expected Hash",
      "type": "string"
    },
    "new_relative_path": {
      "description": "Relative path, including the .md suffix, for the memory file inside its selected memory tree.",
      "title": "New Relative Path",
      "type": "string"
    },
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    }
  },
  "required": [
    "address",
    "new_relative_path",
    "expected_hash"
  ],
  "title": "move_memoryArguments",
  "type": "object"
}
sha256:e7ddac0ffe4ecc341c80830f9388909480f1bed2191f9f496d6b3470746d8d3b

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:be22aa7693662a486dc220634da30019c4bd89b94722191994565401f1ac7787

Interface hash: sha256:160d4d7c7ec26055dda0bd56cd66949927faeb00d535ec27f64754ebd298d345

Other observed Modelara metadata
{
  "id": "mcp:docmancer/move_memory",
  "title": "Move or rename a memory file",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "move_memory"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:271be96d2afc6f81ec4eab4dbe1d379540d11d4d59c5f68e3b7379f1cd425ec2"
}
tooldestructive0.9.150.9.16
pin_memorydocmancer:tool:pin_memory
Observed interface and hashes

MUTATING: pin one durable line into a canonical memory section. Writes to local disk, machine-wide, so it takes no project_path. The pinned zone is the ONLY part of a canonical section that survives automatic reconciliation, so use this, not edit_memory or write_memory, for any correction, standing preference, or fact the reconciler got wrong or left out. Idempotent: pinning the same line twice changes nothing. Use unpin_memory to reverse it, and canonical_memory to see the result. Parameters: section selects which canonical section to pin into, one of about, preferences, working-principles, or active-projects; text is the complete line to pin, which should read as a standalone statement because it is stored verbatim. Returns an object with the section, its path, and the updated pinned-line count.

Input schema

{
  "properties": {
    "section": {
      "description": "Canonical section to modify. canonical-memory is excluded because it describes the store itself and is regenerated wholesale.",
      "enum": [
        "about",
        "preferences",
        "working-principles",
        "active-projects"
      ],
      "title": "Section",
      "type": "string"
    },
    "text": {
      "description": "Complete durable line to add to the selected canonical section's pinned zone.",
      "title": "Text",
      "type": "string"
    }
  },
  "required": [
    "section",
    "text"
  ],
  "title": "pin_memoryArguments",
  "type": "object"
}
sha256:20aa653bd1bc628a10fcc140d0bab1df99f728027b52f61e17068e50415d908a

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:92acc29563baf32cee199d01fcaa90ca5eb4bf358bdc07589b54138a32e87921

Interface hash: sha256:c1a6fb10a12d56a93627b2949d5deca8c5d6b6dc3a2685eda0bc21c8ad23a20a

Other observed Modelara metadata
{
  "id": "mcp:docmancer/pin_memory",
  "title": "Pin a durable line to canonical memory",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "pin_memory"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:e6ce67e787945576d0da05c39533b1e81cc34da09a300391eb4312b950674cfa"
}
toolwrite0.9.150.9.16
read_memorydocmancer:tool:read_memory
Observed interface and hashes

READ-ONLY: read one curated memory file in full, resolved by stable address, relative path, or exact title. Local disk read with no side effects. Ambiguous title or path matches return every candidate address rather than guessing, so a caller can retry with an exact address. This is also how you obtain the content_hash that edit_memory, move_memory, duplicate_memory, and trash_memory all require. Use search_memory first when you do not already know which file you want. Parameters: address is the docmancer://memory/<id> address, the relative path, or the exact title; project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns an object with the body, frontmatter, address, content_hash, and revision id, or a candidates list when the address was ambiguous.

Input schema

{
  "properties": {
    "address": {
      "description": "Stable docmancer://memory/<id> address, relative path, or exact title of the memory file.",
      "title": "Address",
      "type": "string"
    },
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    }
  },
  "required": [
    "address"
  ],
  "title": "read_memoryArguments",
  "type": "object"
}
sha256:87fea8ecf5ae3e00f97c57566eaa2d8d75cca694323fd13762cb2721eb166a3d

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:fec7c2680df8e01bef378b82d6876cba6a00f75e1f57c76cfc06caee6b9d7e61

Interface hash: sha256:2dd8db5237bff449fbdb3af8000c4484cdb50e19447f40fe740e6b82c8b36b17

Other observed Modelara metadata
{
  "id": "mcp:docmancer/read_memory",
  "title": "Read a memory file",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "read_memory"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:f04d78032b509d56c4e697533b6947fc54e68ed545814d736a48961023f3e2ee"
}
toolread0.9.150.9.16
restore_memorydocmancer:tool:restore_memory
Observed interface and hashes

MUTATING: undo a trash_memory call by restoring one curated memory file from its restore token. Writes to local disk and appends to the change timeline. The file returns to its original path with its address and history intact, so references by address resume working. A token is single-use and only valid for the tree it was issued against, so a spent or foreign token fails without changing anything. Restoring is only possible while the token is known: there is no way to browse trash from MCP. Parameters: restore_token is the exact token returned by the trash_memory call being undone; project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns an object with the restored address, path, and revision id.

Input schema

{
  "properties": {
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    },
    "restore_token": {
      "description": "Restore token returned by a prior trash_memory call, identifying the file to restore.",
      "title": "Restore Token",
      "type": "string"
    }
  },
  "required": [
    "restore_token"
  ],
  "title": "restore_memoryArguments",
  "type": "object"
}
sha256:d9d7a72a2dfb0e0e38b48e9719c49c829e837fbb16cdf8bb0a6a03dc0ed15193

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:0dd13bf019ac295ef563b4c1d39e93cf8718fe71fedb749d96d96aaa7cee92f9

Interface hash: sha256:2aea142b1150ae47e04126433d93f44e40312a8cba4e5e69940aaff2bf5d89cd

Other observed Modelara metadata
{
  "id": "mcp:docmancer/restore_memory",
  "title": "Restore a trashed memory file",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "restore_memory"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:b5a3e63941cfa552bb3810182cae395cbec99cecb5c4722937037ca444b0b688"
}
toolwrite0.9.150.9.16
search_docsdocmancer:tool:search_docs
Observed interface and hashes

READ-ONLY: search the local documentation index built by `docmancer docs add`, covering library, API, and vendor documentation the user chose to ingest. Runs entirely locally; no network call, so it only ever returns docs already added on this machine and returns [] when none have been. Use it for version-specific library or vendor behaviour. Not for anything about this user or their projects: use search_memory, search_evidence, or ask_memory for that. Parameters: query is the natural-language text to match against the indexed documentation; limit caps the number of results (default 8). Returns a list of objects with the matching excerpt, its source document, and a relevance score.

Input schema

{
  "properties": {
    "limit": {
      "default": 8,
      "description": "Maximum number of matching results to return. Defaults are tool-specific.",
      "title": "Limit",
      "type": "integer"
    },
    "query": {
      "description": "Natural-language terms to search for in the local memory or documentation index.",
      "title": "Query",
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_docsArguments",
  "type": "object"
}
sha256:abb354f0d382f7d84d2b7ff3df9fba0b5e644ccb85d724ef251ac5563d3482d8

Output schema

{
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "search_docsOutput",
  "type": "object"
}
sha256:64ba9e9c4ade05fdefc6a97819fdc4b9bea54c0b03ee7c7c4fe46b3cc8e55ed2

Description hash: sha256:198b32394498a89af25b20571e12625f9c905125714d0cb444e2d3d34f086456

Interface hash: sha256:a7528c1f11c767c76ea345ab2813d287d6a39c28184fc405d5f1ae86fd7c3109

Other observed Modelara metadata
{
  "id": "mcp:docmancer/search_docs",
  "title": "Search local documentation index",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "search_docs"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:2398b705ca6e46aef0b323361c2e42974b0d03ea26153d5bb1680b9855afc754"
}
toolread0.9.150.9.16
search_evidencedocmancer:tool:search_evidence
Observed interface and hashes

READ-ONLY: semantic search over the raw evidence index, meaning the memory, instruction, and rule files that other coding agents already wrote on this machine and that docmancer harvested. Runs entirely locally against the embedding index; no network call, no cost. Use it to find what an agent originally recorded, with a relevance score and the file it came from. Not for curated memory you or an agent deliberately wrote: that lives in a separate tree, so use search_memory for it, or ask_memory to get both at once. Parameters: query is the natural-language text to match; limit caps the number of results (default 8); include_history adds superseded evidence to the active evidence; expand_relations adds items linked to a direct match. Returns a list of objects with score, excerpt, source_path, scope, kind, lifecycle_state, and a docmancer://record/<id> record_uri. Returns [] when nothing matches.

Input schema

{
  "properties": {
    "expand_relations": {
      "default": false,
      "description": "When true, include related memory items alongside direct matches.",
      "title": "Expand Relations",
      "type": "boolean"
    },
    "include_history": {
      "default": false,
      "description": "When true, include historical or superseded memory evidence in addition to active evidence.",
      "title": "Include History",
      "type": "boolean"
    },
    "limit": {
      "default": 8,
      "description": "Maximum number of matching results to return. Defaults are tool-specific.",
      "title": "Limit",
      "type": "integer"
    },
    "query": {
      "description": "Natural-language terms to search for in the local memory or documentation index.",
      "title": "Query",
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_evidenceArguments",
  "type": "object"
}
sha256:d66f51ff1a20b41fc1ee9081587c58c8d020d4f5f06e70eb481ce4307ea79aa8

Output schema

{
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "search_evidenceOutput",
  "type": "object"
}
sha256:3a30d5fbeac0aa251d4089004d8c0556824f908dec83a8b7738c732a6867f61d

Description hash: sha256:995d155e9df130fa7f8b468ec209bc350212fa4bdaf78d19caf84d67ec221b8f

Interface hash: sha256:f2c0a7085f72a2e10a8b1d0f3355df7d75986ac14632194ba850cbe89593e7fa

Other observed Modelara metadata
{
  "id": "mcp:docmancer/search_evidence",
  "title": "Search harvested agent evidence",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "search_evidence"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:e4f405e0c3146e72fff07c8891e6962244278c6e45607206ecd327eb311e9eb5"
}
toolread0.9.150.9.16
search_memorydocmancer:tool:search_memory
Observed interface and hashes

READ-ONLY: lexical search over the curated memory tree, meaning the decisions, constraints, and conventions deliberately written by the user or an agent. Local disk read, no embedding call, no cost. Only active entries are searched; archived and trashed files are excluded. Returns [] rather than an error when nothing is relevant or the tree is empty, so an empty result is a real answer and not a failure. Not the same store as search_evidence, which searches raw harvested agent files instead; use ask_memory when you want both stores plus mandatory policy in one bundle. Parameters: query is the natural-language text to match; limit caps the number of results (default 8, capped at 50); project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns a list of objects with the docmancer://memory address, title, excerpt, authority, and source_type. Pass an address to read_memory for the full file.

Input schema

{
  "properties": {
    "limit": {
      "default": 8,
      "description": "Maximum number of matching results to return. Defaults are tool-specific.",
      "title": "Limit",
      "type": "integer"
    },
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    },
    "query": {
      "description": "Natural-language terms to search for in the local memory or documentation index.",
      "title": "Query",
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_memoryArguments",
  "type": "object"
}
sha256:a36d823800a06a39df8781c400e7cc571624bcdd47a6dca68ae7621237104531

Output schema

{
  "properties": {
    "result": {
      "anyOf": [
        {
          "items": {
            "additionalProperties": true,
            "type": "object"
          },
          "type": "array"
        },
        {
          "additionalProperties": true,
          "type": "object"
        }
      ],
      "title": "Result"
    }
  },
  "required": [
    "result"
  ],
  "title": "search_memoryOutput",
  "type": "object"
}
sha256:d2a09a641ffffed655102c7aac0d14e98fdf569532c910245e331a4036ae7b41

Description hash: sha256:0b552ce0a21a2c37772e127fd2ab608ab8306d862c594d4913c25e5a40d8d276

Interface hash: sha256:e759d79a6dc6a4196ab9f7924a015183d768d21488ee0557435528bdd399e453

Other observed Modelara metadata
{
  "id": "mcp:docmancer/search_memory",
  "title": "Search curated memory",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "search_memory"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:f3a37a5b319ed2ee3a0ee088ce5d24601847b9471a081e83b7e9a4ff7d116a68"
}
toolread0.9.150.9.16
trash_memorydocmancer:tool:trash_memory
Observed interface and hashes

DESTRUCTIVE BUT REVERSIBLE: move one curated memory file to trash so it stops being read or recalled. Writes to local disk and appends to the change timeline. Nothing is erased: the call returns a restore_token that restore_memory consumes to bring the file back, so keep that token in your reply if the user might change their mind. Guarded by expected_hash, so a stale hash fails without trashing anything. Prefer setting status='archived' with write_memory when the file should stay readable but stop being recalled. Parameters: address identifies the file to trash; expected_hash is its current content_hash from read_memory, confirming you are discarding the revision you actually saw; project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns an object with the trashed address and the restore_token needed to undo it.

Input schema

{
  "properties": {
    "address": {
      "description": "Stable docmancer://memory/<id> address, relative path, or exact title of the memory file.",
      "title": "Address",
      "type": "string"
    },
    "expected_hash": {
      "description": "The file's current content_hash from a prior read_memory call. A stale value fails safely instead of overwriting a newer revision.",
      "title": "Expected Hash",
      "type": "string"
    },
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    }
  },
  "required": [
    "address",
    "expected_hash"
  ],
  "title": "trash_memoryArguments",
  "type": "object"
}
sha256:6aa5f93c4aa5ff99ecc80e9ee2ac70b46cf90c2b37291b59d5337d412b16981c

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:df2a3f2d86fe4572769888f1e9dba3952694332f8c622a77dc33c4f27dc0a622

Interface hash: sha256:b8f733584c038ab2dce5d6e9dda82e55b4b3e4bc300a6f7f451a8cf3f37bb9e8

Other observed Modelara metadata
{
  "id": "mcp:docmancer/trash_memory",
  "title": "Trash a memory file",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "trash_memory"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:b0758f19f0d3ad41491e5aac9f45c00dc575de2c3944b40e205bdf7ebf0769f1"
}
tooldestructive0.9.150.9.16
unpin_memorydocmancer:tool:unpin_memory
Observed interface and hashes

MUTATING and DESTRUCTIVE: permanently remove pinned lines from a canonical memory section by case-insensitive substring match, with no undo and no restore token. Writes to local disk, machine-wide, so it takes no project_path. A substring can match more lines than intended, so read the section with canonical_memory first and pass text specific enough to hit only what you mean. Fails without changing anything when nothing matches, which makes a dry run safe. Only pinned lines are removable; generated content is rewritten by reconciliation instead. Parameters: section selects which canonical section to modify, one of about, preferences, working-principles, or active-projects; text is the case-insensitive substring, not a whole line and not a pattern, identifying the pinned lines to delete. Returns an object with the section and how many lines were removed.

Input schema

{
  "properties": {
    "section": {
      "description": "Canonical section to modify. canonical-memory is excluded because it describes the store itself and is regenerated wholesale.",
      "enum": [
        "about",
        "preferences",
        "working-principles",
        "active-projects"
      ],
      "title": "Section",
      "type": "string"
    },
    "text": {
      "description": "Case-insensitive substring identifying pinned lines to remove from the selected section.",
      "title": "Text",
      "type": "string"
    }
  },
  "required": [
    "section",
    "text"
  ],
  "title": "unpin_memoryArguments",
  "type": "object"
}
sha256:8f92bc5323a896c3b3eadc0ab00988afb50938f551623190ad064d6205e51988

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:de687311d5be7aca47c0296bfc22a1c49aedd05d423964922db951a8e02c3e78

Interface hash: sha256:b4065ec802761033a8122dce04f945453b99b2f23891690c6ac3ee5aa1d37a81

Other observed Modelara metadata
{
  "id": "mcp:docmancer/unpin_memory",
  "title": "Remove pinned lines from canonical memory",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "unpin_memory"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:87c468cee39ff83623fe250d1f305510c8807c85c4a0111ee97e2021607317b7"
}
tooldestructive0.9.150.9.16
write_memorydocmancer:tool:write_memory
Observed interface and hashes

MUTATING: create or update one curated memory file in the memory tree, addressed as docmancer://memory/<id>. Writes to local disk and appends to the change timeline; never silently clobbers, because the expect guard decides whether an existing file may be replaced. Use it to record a durable decision, constraint, or convention. Not for correcting the reconciled canonical memory about the user, which is regenerated and would discard the edit: use pin_memory for that. To change only the body of an existing file, prefer edit_memory. Parameters: relative_path is the file's path in the tree and must include the Markdown suffix; text is the full Markdown body; expect is the write guard, 'absent' (default) to create only and fail if the path exists, or the current content_hash to permit a guarded overwrite; memory_type, scope, authority, status, and curation_origin are frontmatter labels described in the schema; project_id names the owning project; sources lists backing file paths or URLs; tags lists retrieval labels; project_path project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project. Returns an object with the stable address, the new content_hash, and the revision id, all of which later guarded calls need.

Input schema

{
  "properties": {
    "authority": {
      "default": "advisory",
      "description": "How binding the memory is. mandatory entries are always included in a recall bundle; advisory entries compete on relevance. Defaults to advisory.",
      "enum": [
        "advisory",
        "mandatory"
      ],
      "title": "Authority",
      "type": "string"
    },
    "curation_origin": {
      "default": "deliberate_write",
      "description": "Free-form origin label stored in frontmatter recording how the memory was created. Defaults to deliberate_write.",
      "title": "Curation Origin",
      "type": "string"
    },
    "expect": {
      "default": "absent",
      "description": "Create/update guard, and not an enum: pass the literal string absent for create-only, or the file's current content_hash for a guarded update.",
      "title": "Expect",
      "type": "string"
    },
    "memory_type": {
      "default": "fact",
      "description": "Free-form memory classification stored in frontmatter. Defaults to fact.",
      "title": "Memory Type",
      "type": "string"
    },
    "project_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project identifier stored in the memory file frontmatter. Omit unless the memory belongs to a named project.",
      "title": "Project Id"
    },
    "project_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Project root whose memory tree the operation applies to. Omit it to use the machine-wide tree, and always omit it when this server was started pinned to a project.",
      "title": "Project Path"
    },
    "relative_path": {
      "description": "Relative path, including the .md suffix, for the memory file inside its selected memory tree.",
      "title": "Relative Path",
      "type": "string"
    },
    "scope": {
      "default": "global",
      "description": "Memory visibility scope stored in frontmatter. Use global for machine-wide memory or project for project-scoped memory.",
      "enum": [
        "global",
        "project"
      ],
      "title": "Scope",
      "type": "string"
    },
    "sources": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Source references that back the memory content.",
      "title": "Sources"
    },
    "status": {
      "default": "active",
      "description": "Free-form lifecycle status stored in frontmatter. Only active entries are recalled. Defaults to active.",
      "title": "Status",
      "type": "string"
    },
    "tags": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Labels used to classify and retrieve the memory content.",
      "title": "Tags"
    },
    "text": {
      "description": "Markdown body to write or replace. Replaces the body wholesale; it is not appended.",
      "title": "Text",
      "type": "string"
    }
  },
  "required": [
    "relative_path",
    "text"
  ],
  "title": "write_memoryArguments",
  "type": "object"
}
sha256:ae306bd98486d8a5082c9ebcdcc2778d0ba50ef0c4915018dc465838f08fdab6

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:2892df75dd904345229cc25c0a61c7b6dc394049acfc7af32c1c8a665debda52

Interface hash: sha256:6a30b03f6bd6a6d4a70021b432569678a3994fda09c5ad791a75d583a9f0b1f9

Other observed Modelara metadata
{
  "id": "mcp:docmancer/write_memory",
  "title": "Create or update a memory file",
  "source": {
    "type": "mcp",
    "server": "docmancer",
    "operation": "write_memory"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:85052ff63243d6f193e719341c9aa9fee3836e271f552f77522d5cab14b4c501"
}
toolwrite0.9.150.9.16

STATIC COMPARISONS

Release history

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

    Nov 16, 2026· Automated static analysis

  2. 0 added0 removed3 schema0 write0 destructive0 unknown

    Nov 16, 2026· Pending human review