Developer-tools MCP server

plur

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

View watchlist

DistributionDistribution: npm
Package@plur-ai/mcp
Latest analyzed version0.23.0
Current tool count15
Latest analysisNov 17, 2026
Package source

OBSERVED INTERFACE

Capability surface

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

3 releases analyzed0.22.0 → 0.23.0Latest: 0.23.0
  • read3
  • write6
  • destructive6
  • 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
@plur-ai/mcp@0.23.0
Registry
npm
Published
Oct 30, 2026
Integrity
sha512-HAHnRYpiBz2Y5s3uPmF/5PLFV2I+Je7QvLmBAHWuJJumJcKzT3wfHX55mC+ZiBOYWKLfaLUI7XrMDo/xDG0rKA==
Analyzer
modelara v0.1.8 · policy not recorded
Repository
https://github.com/plur-ai/plur

15 capabilities

CapabilityTypeDerived effectFirst observed in Valyd coverageLast changed
plur_adminplur-ai-plur:tool:plur_admin
Observed interface and hashes

Gateway to the 30 PLUR operations that are not top-level tools under the current profile (collapsed into one dispatch tool so Cursor's ~40-tool-per-workspace limit is not exhausted by PLUR alone). A plur_* name missing from tools/list means it moved HERE — not that the MCP is unavailable. Calling convention: { action: "<tool name>", args: { ...that tool's normal arguments } } — same arguments, same validation, same result as a direct call. Example: { action: "plur_recall_hybrid", args: { query: "deploy checklist" } }. Send { action: "help" } for every action's one-line description and argument schema. Actions, grouped — inject: plur_inject, plur_inject_hybrid · packs: plur_packs_discover, plur_packs_export, plur_packs_install, plur_packs_list, plur_packs_preview · stores: plur_stores_add, plur_stores_list · sync: plur_sync, plur_sync_status · other: plur_capture, plur_episode_to_engram, plur_extract_meta, plur_history, plur_ingest, plur_learn_batch, plur_meta_engrams, plur_outbox, plur_pin, plur_profile, plur_promote, plur_provenance, plur_recall_hybrid, plur_rescope, plur_scopes_discover, plur_session_scope, plur_similarity_search, plur_suggest_scope, plur_timeline.

Input schema

{
  "properties": {
    "action": {
      "description": "Which underlying plur_* tool to invoke, or \"help\" to list every action with its description and argument schema",
      "type": "string"
    },
    "args": {
      "additionalProperties": true,
      "description": "Arguments for the chosen action, matching that tool's normal input schema",
      "type": "object"
    }
  },
  "required": [
    "action"
  ],
  "type": "object"
}
sha256:347fca3883c19b430e31b79482d1edbe79c7c4571d2de2e4a5dab942867a7f9d

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:3cc00f360d839ca221b57e43ae48a6768bcea7740456abe9669a8ecba4bcd75a

Interface hash: sha256:dbcd9df2833ef49d88671f1da632899cc7bea4e2b64e0789719b4fc95c6ef7c3

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_admin",
  "title": "Admin dispatch",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_admin"
  },
  "declared": {
    "read_only": "false",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:0ad490eab8494aa6f486ff2172a40f6b7ad77cba41372abfa4bfe094a9a5ae7f"
}
toolwrite0.22.0No change observed
plur_doctorplur-ai-plur:tool:plur_doctor
Observed interface and hashes

Diagnose the PLUR ENGINE (embedder, hybrid search, remote-store auth) — not hook/MCP wiring. Reports whether the embedding model loaded, whether hybrid search is fully operational, and — for any configured enterprise/remote store — whether its auth is valid (probes /api/v1/me and decodes token expiry), so a dead or soon-to-expire token surfaces instead of hiding behind a "healthy" report. Run this first when recall feels off or team engrams stop syncing. Does NOT check .cursor/mcp.json, .cursor/hooks.json, or the live MCP tool count — for that, run the `plur doctor` CLI command in a terminal (a different, more thorough check with the same name).

Input schema

{
  "properties": {
    "rerank_eval": {
      "description": "If true and a reranker is configured (PLUR_RERANKER), run the per-store self-eval gate (#451): probes synthesized from this store's own engrams compare rerank-on vs RRF-only ordering. Verdict is cached in the store and advisory — it never auto-disables reranking. Costs one cross-encoder pass per probe (~20 probes).",
      "type": "boolean"
    },
    "retry": {
      "description": "If true, reset cached embedder failure state and retry the model load before reporting",
      "type": "boolean"
    }
  },
  "type": "object"
}
sha256:bd4c8f8e28a455597f409b746824d6293e5cd61e6c02356b320c93131c856fee

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:b4d00ef3df05f328fd226e86dcb19f75021584e136374c6cb655b5d1826e7c4a

Interface hash: sha256:03568789db490b0f50f6224c42d78c28cf480ac6d4eeed6fa62e0442f0e83330

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_doctor",
  "title": "Doctor",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_doctor"
  },
  "declared": {
    "read_only": "false",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:8099fc32694551ab664afbec389b7799b67603af2b8fe0cce7eab60294e12749"
}
toolwrite0.22.0No change observed
plur_feedbackplur-ai-plur:tool:plur_feedback
Observed interface and hashes

Rate an engram's usefulness — trains injection relevance over time. Supports single or batch mode.

Input schema

{
  "properties": {
    "id": {
      "description": "Engram ID (single mode)",
      "type": "string"
    },
    "scope": {
      "description": "Store scope to target directly, e.g. \"primary\" for the local store or a remote scope like \"group:plur/plur-ai/engineering\". Required when the same engram ID exists in multiple stores (#850).",
      "type": "string"
    },
    "signal": {
      "description": "Feedback signal (single mode)",
      "enum": [
        "positive",
        "negative",
        "neutral"
      ],
      "type": "string"
    },
    "signals": {
      "description": "Batch feedback signals",
      "items": {
        "properties": {
          "id": {
            "description": "Engram ID",
            "type": "string"
          },
          "scope": {
            "description": "Store scope to target directly (optional, same semantics as top-level scope).",
            "type": "string"
          },
          "signal": {
            "enum": [
              "positive",
              "negative",
              "neutral"
            ],
            "type": "string"
          }
        },
        "required": [
          "id",
          "signal"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "type": "object"
}
sha256:7fa379ac1cc7a80da4a927e23dc9d73d55830593cdcedebcdfa7f410dccb2b55

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:ee61f60dd1013bc893e9e6b22b83c3708e2f4f4a28ff8eece9c639dd4365066b

Interface hash: sha256:711087e06552687ebcbaf3ffc71d164d3482708c9cdffb51f4f54aee8ae9da0a

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_feedback",
  "title": "Feedback",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_feedback"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:1aa0fc7c636dff2ee6fa6bdb895817c2c5dbfb2ed6b168b2b7f14b8dd598e4bf"
}
toolwrite0.22.0No change observed
plur_forgetplur-ai-plur:tool:plur_forget
Observed interface and hashes

Retire an engram by ID or search term — marks it as no longer active without deleting history

Input schema

{
  "properties": {
    "id": {
      "description": "Exact engram ID to retire",
      "type": "string"
    },
    "reason": {
      "description": "Why this is being retired. Recorded in the history log and on the engram (#959). Say what changed, not just that something did.",
      "type": "string"
    },
    "scope": {
      "description": "Which store holds it (#831). Ids are minted per store, so one id can name several unrelated engrams. Pass \"primary\" to stay on disk — the local primary store and any local secondary stores, never a remote — or a remote scope (e.g. \"group:plur/plur-ai/engineering\") to target that server. A scope matching no configured store is rejected, not guessed at. Omit it and an id resolving in two places is refused.",
      "type": "string"
    },
    "search": {
      "description": "Search term to find engram to retire",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:e817bdb655d26fcb4c2c2d4426a501025631b421d9a867949678020ee7dc27ca

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:6583ebf31b43da816c9fc2def61586c2584ce6343b775594ae4334216e0ce58b

Interface hash: sha256:90b5f2f227b825f7a5fa9d292c46d1ca9bdc7b53a8f8fc8f24218c4dd0ec4b52

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_forget",
  "title": "Forget",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_forget"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "true",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "unknown"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:2d3eb9f03a1473bd89f00c24884d6f6bebcd78248b3f06d0b02c94702ae6dce1"
}
tooldestructive0.22.0No change observed
plur_learnplur-ai-plur:tool:plur_learn
Observed interface and hashes

Create an engram — record a reusable learning, preference, or correction. A write is never suppressed by similarity: exact content-hash duplicates NOOP, and anything merely SIMILAR is written and reported back in `dedup.near_duplicates` (closest existing engrams, their cosine scores, and a preview of each neighbour's own statement — read them before moving on; that is what they are for) so you can supersede or merge deliberately. High similarity is a reason to look, not a decision — cosine cannot tell a duplicate from a correction of it. Multi-agent note: in an orchestration that spawns subagents, have the PARENT session own plur_learn writes — spawned subagents should return their findings as text for the parent to persist, rather than each calling plur_learn (tool availability is not guaranteed in every subagent context). See plur-ai/plur#281.

Input schema

{
  "properties": {
    "attribution": {
      "description": "Who is answerable for this memory (#961). Every sub-field optional; OMIT rather than guess — a memory with no agent is honest, one with an invented agent is worse than none. Set asserted_by to \"unidentified\" when nobody is identified, rather than leaving it out: absence cannot be told apart from a memory written before this existed.",
      "properties": {
        "asserted_by": {
          "description": "Who or what asserted it. Any address: a local name, a Decentralized Identifier, or \"unidentified\".",
          "type": "string"
        },
        "model": {
          "description": "The model behind the statement, if one was involved. Prompt TEXT is never stored, only a hash.",
          "properties": {
            "name": {
              "type": "string"
            },
            "prompt_id": {
              "type": "string"
            },
            "prompt_sha256": {
              "type": "string"
            },
            "prompt_version": {
              "type": "string"
            }
          },
          "type": "object"
        },
        "on_behalf_of": {
          "description": "The party the runtime acted for.",
          "type": "string"
        },
        "runtime": {
          "description": "The software writing this. Usually known, so usually worth setting.",
          "properties": {
            "name": {
              "type": "string"
            },
            "version": {
              "type": "string"
            }
          },
          "type": "object"
        },
        "tool": {
          "description": "An extractor or importer, with its version.",
          "properties": {
            "name": {
              "type": "string"
            },
            "version": {
              "type": "string"
            }
          },
          "type": "object"
        }
      },
      "type": "object"
    },
    "claim_class": {
      "description": "What KIND of claim this is (#963), and the most useful single field for anyone later deciding how much to trust it. Use \"asserted\" when a PERSON stated it outright, \"inferred\" when YOU worked it out, \"documented\" when you took it from prose someone wrote, \"observed\" for a record of something that happened, \"structural\" when read off the shape of an artifact, \"revised\" for a rewrite. Omit only when it genuinely cannot be determined.",
      "enum": [
        "observed",
        "documented",
        "structural",
        "asserted",
        "inferred",
        "revised"
      ],
      "type": "string"
    },
    "commitment": {
      "description": "How firmly the user has committed to this belief (default: leaning). `draft` marks the engram as pending human approval: core stores and RECALLS it normally but NEVER injects it (#1141), so an unapproved rule cannot shape agent behaviour. Retrieval stays open because reviewing something requires reading it.",
      "enum": [
        "exploring",
        "leaning",
        "decided",
        "locked",
        "draft"
      ],
      "type": "string"
    },
    "domain": {
      "description": "Domain tag, e.g. software.deployment",
      "type": "string"
    },
    "license": {
      "description": "Which licence governs reuse of this memory, as an SPDX-style identifier such as \"cc-by-4.0\" or \"apache-2.0\". Set it only when the user has actually said which licence applies — do NOT guess one. Left unset, a default applies that nobody chose, and a provenance record reports it as unchosen rather than presenting it as a decision.",
      "type": "string"
    },
    "locked_reason": {
      "description": "Why this engram is locked (only meaningful when commitment=locked)",
      "type": "string"
    },
    "measured_under": {
      "description": "Measurement context for numeric or benchmark-derived claims (#869). Records the conditions under which the asserted value was measured — model, source_type, hardware, dataset, date. When present, the tension scanner does not treat two measurements from the same store taken under different configurations as a contradiction (the skipped pair is reported in the scan result). Omit for non-numeric engrams.",
      "properties": {
        "dataset": {
          "description": "Dataset or workload identifier (e.g. \"LongMemEval-S\", \"plur-bench-2026-Q2\")",
          "type": "string"
        },
        "date": {
          "description": "ISO date (YYYY-MM-DD) the measurement was taken",
          "type": "string"
        },
        "hardware": {
          "description": "Hardware or runtime tier (e.g. \"M3-Pro-36GB\", \"A100\", \"CI-runner\")",
          "type": "string"
        },
        "model": {
          "description": "Model or system variant (e.g. \"claude-opus-4\", \"gpt-4o\")",
          "type": "string"
        },
        "source_type": {
          "description": "Source environment type (e.g. \"local-git\", \"gitlab\", \"bench\", \"production\")",
          "type": "string"
        }
      },
      "type": "object"
    },
    "pinned": {
      "description": "Always-load flag. If true, this engram bypasses the keyword-relevance gate at injection time. Use sparingly: meta-rules, safety conventions, core operating principles only.",
      "type": "boolean"
    },
    "rationale": {
      "description": "The mechanism that makes the statement true, and therefore the condition under which it would STOP being true. One sentence. \"Because the user said so on <date>\" is a citation, not a mechanism: that belongs in `source`. This text is indexed, so a real mechanism also carries concrete nouns a future query can match. NOTE: constraints render without rationale (plur-ai/plur#1144), so a mechanism a prohibition needs the model to weigh must stay in the statement.",
      "type": "string"
    },
    "scope": {
      "description": "Namespace, e.g. global, project:myapp",
      "type": "string"
    },
    "session_id": {
      "description": "Session this write belongs to (from plur_session_start). Resolves the session default scope (incl. mid-session plur_session_scope changes) when no explicit scope is passed. Optional when one session is open. With none or several open and no session_id, NO session default applies: the write takes the unscoped path (#243, E7).",
      "type": "string"
    },
    "source": {
      "description": "Origin of this knowledge (URL, conversation ref, etc.)",
      "type": "string"
    },
    "statement": {
      "description": "ONE assertion, written so someone who was not there can act on it. Route the rest to the field whose job it is: the mechanism that makes it true goes in `rationale`, where it came from in `source`, when it applies in `tags`/`domain`. An \"and also\" means a second engram. Good: \"Never name a client unless the user names them first, say the customer.\" Typical 100-300 chars; past ~600 you are carrying another field content. Length is a symptom, not the rule.",
      "type": "string"
    },
    "supersedes": {
      "description": "Engram IDs this statement intentionally replaces (#240). Writes relations.supersedes on the new engram and the reverse superseded_by edge on each local target. Supersedes-linked pairs are skipped by tension scans — an intentional update is not a contradiction. Use when updating a standing fact (new version, changed rule) rather than contradicting it.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "tags": {
      "description": "Searchable keyword tags — contribute to BM25/embedding recall, so concrete keywords pay off",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "type": {
      "description": "Category of the engram",
      "enum": [
        "behavioral",
        "terminological",
        "procedural",
        "architectural"
      ],
      "type": "string"
    },
    "valid_from": {
      "description": "ISO date (YYYY-MM-DD) the knowledge becomes valid — inject/recall skip the engram before this date (#347)",
      "type": "string"
    },
    "valid_until": {
      "description": "ISO date (YYYY-MM-DD) the knowledge expires — inject/recall skip the engram after this date. Set this for any time-bound fact (offers, deadlines, temporary endpoints). When omitted, an explicit expiry phrase in the statement (\"valid until 31 May 2026\") is auto-parsed and echoed back (#347)",
      "type": "string"
    },
    "visibility": {
      "description": "Who this memory is shared with beyond its scope. Defaults to \"private\": EXCLUDED from every exported pack and from shared git sync. The default does NOT keep a team-scope write on this machine — with visibility omitted, a write whose scope is a team store (e.g. group:acme/eng) still goes to that team store. Only an EXPLICIT \"private\" keeps such a write local (stored here with a warning, never sent to the team store). Set \"public\" only when the user has said this is shareable with others — it is their decision, not yours. Without \"public\" nothing an agent writes can appear in a pack.",
      "enum": [
        "private",
        "public",
        "template"
      ],
      "type": "string"
    }
  },
  "required": [
    "statement"
  ],
  "type": "object"
}
sha256:1feef0d0d91bdfb2fb860f1c0dade23b689fabae35efeda62ffecfdf934374f8

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:514b57693e8efda7f10d4f1fc243107fb2baff359639e8ac8336d418b428448d

Interface hash: sha256:7a1574d1650fbad94d77599f8d9c158874b85e7afa11dfb3081be890a0925b8d

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_learn",
  "title": "Learn",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_learn"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:2d2cf5855e695c5ba8d651c18c94493cfd2186818d95071e5e9286f63ca34017"
}
toolwrite0.22.0No change observed
plur_packs_uninstallplur-ai-plur:tool:plur_packs_uninstall
Observed interface and hashes

Uninstall an engram pack by name — removes the pack and all its engrams

Input schema

{
  "properties": {
    "name": {
      "description": "Pack name to uninstall (use plur_packs_list to see names)",
      "type": "string"
    }
  },
  "required": [
    "name"
  ],
  "type": "object"
}
sha256:a5e5d90e2c74e90139430cbd0e8d12e6d8a5b4f9e945d0de90a33f37319ce74b

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:010ec48a2475ce52fd5bf7a8bfd633f1d071c6c281cea205aa9c6a17bb8cafb8

Interface hash: sha256:cb8b90dfa4146c4a12fe6d598bc689ddf5191701379c5cd0dac9f7f3ac50ca4a

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_packs_uninstall",
  "title": "Uninstall pack",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_packs_uninstall"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:2f94a637696a1a90da2ea62a8b197152a8f1c881fd4303a11cd814e76c94d14e"
}
tooldestructive0.22.0No change observed
plur_recallplur-ai-plur:tool:plur_recall
Observed interface and hashes

Search engrams by topic. Default mode is hybrid (BM25 + local embeddings via RRF) — set mode:"keyword" for BM25-only. Local search plus, when a configured enterprise store is part of the current project/work — or when the scope (or the default scope this session registered itself) is a personal user: scope and a remote store is configured with that same scope (exact match, case-insensitive; that rule adds only the matching store, though a store set to dial: always or a trusted project remote can still add others) — one live timeout-bounded recall per remote host merged in (a `remote_stores` block + warning appears when a host is degraded; no host configured or implicated = fully local). Note: a project-scope filter also returns personal-family engrams (local, global, user:*, agent:*); an explicit scope=global recall returns ALL personal-family engrams — wider than scope=global INJECT, which is targeted to the global namespace only.

Input schema

{
  "properties": {
    "budget": {
      "description": "Budget constraints for sub-agents. Hybrid mode only — ignored when mode:\"keyword\".",
      "properties": {
        "max_results": {
          "type": "number"
        },
        "max_tokens": {
          "type": "number"
        }
      },
      "type": "object"
    },
    "caller_session_id": {
      "description": "Session ID of calling agent for budget enforcement. Hybrid mode only — ignored when mode:\"keyword\".",
      "type": "string"
    },
    "domain": {
      "description": "Filter by domain prefix",
      "type": "string"
    },
    "include_episodes": {
      "description": "If true, include linked episode summaries for each engram (SP2 episodic anchoring). Hybrid mode only — ignored when mode:\"keyword\".",
      "type": "boolean"
    },
    "limit": {
      "description": "Max results to return (default 20)",
      "type": "number"
    },
    "mode": {
      "description": "Search mode — hybrid (default): BM25 + embeddings via RRF; keyword: BM25-only (faster, embeddings-independent). budget, caller_session_id and include_episodes apply to hybrid mode only — in keyword mode use limit to bound results.",
      "enum": [
        "hybrid",
        "keyword"
      ],
      "type": "string"
    },
    "query": {
      "description": "Search query to find relevant engrams",
      "type": "string"
    },
    "scope": {
      "description": "Filter by scope (also includes global)",
      "type": "string"
    },
    "session_id": {
      "description": "Session this recall belongs to (from plur_session_start). Its default scope (incl. mid-session plur_session_scope changes) sets the remote dialing context when no explicit scope filter is passed. Optional when one session is open (#243); with none or several open and no session_id, no session default applies.",
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "type": "object"
}
sha256:ebfcf933bebf7178366fa7c3e927fb2d8a36f0b97814660193b65294d5b7496a

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:7f923bb5663104536d211fed5fb65f45f4fc5b135139e47b4dd423f2bb139a39

Interface hash: sha256:560d37b55e5d464d8eb080efa705c5c65d89f1e5d300bad91314bc8a5d8bdcf4

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_recall",
  "title": "Recall",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_recall"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "true",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:93a13b91e342c5828ee08cfe7a588fa2faf3f7028a6bcfc1bee600f6ae58bfa4"
}
toolread0.22.0No change observed
plur_receiptplur-ai-plur:tool:plur_receipt
Observed interface and hashes

Counted report of what your memory retrieved for you: engrams stored, how many were retrieved and how often, which are most relied on, and how much of the store is dormant. Local and read-only; every figure is directly counted, never estimated. IMPORTANT when relaying to the user: `activation_rate` is COVERAGE over the logging window (≈ how much of the store was surfaced), NOT a quality or effectiveness score — it is naturally low and FALLS as more engrams are added, so never present it as "memory is N% effective". A `summary` line is included; prefer relaying that. NOT plur_provenance: this counts usage across the whole store; plur_provenance says where a single memory came from.

Input schema

{
  "properties": {
    "days": {
      "description": "Restrict to the last N days (integer). Omit for all recorded history.",
      "type": "number"
    }
  },
  "type": "object"
}
sha256:1ab4528d04d7be1bb673ed3c643ce4b0a5fb52c5c30265927aff5fcd45eb69c5

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:3417c3a5d7501d2bca86b7b9de19588fc36825b4ccb62730bf6fc5a37c92094c

Interface hash: sha256:2bba11181958d82c5e322bb7cf4d2d0c885f27e9aa1d02918faa8cf2f66692d5

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_receipt",
  "title": "Memory receipt",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_receipt"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "true",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:f93331b7c118cf2a0061ac1fcc36cfc6b3c79c3351890bb38e8c61acfdaa608f"
}
toolread0.22.0No change observed
plur_report_failureplur-ai-plur:tool:plur_report_failure
Observed interface and hashes

Report a failure for a procedural engram — triggers procedure evolution via LLM if configured. Only works on procedural engrams. Max 3 revisions per procedure per 24h.

Input schema

{
  "properties": {
    "engram_id": {
      "description": "ID of the procedural engram that failed",
      "type": "string"
    },
    "failure_context": {
      "description": "Description of what went wrong when following this procedure",
      "type": "string"
    },
    "llm_api_key": {
      "description": "API key for the LLM",
      "type": "string"
    },
    "llm_base_url": {
      "description": "OpenAI-compatible API base URL for procedure evolution",
      "type": "string"
    },
    "llm_model": {
      "description": "Model name (default: gpt-4o-mini)",
      "type": "string"
    }
  },
  "required": [
    "engram_id",
    "failure_context"
  ],
  "type": "object"
}
sha256:cce9085dd031dcd030fe4c18c388bad3756ab43fbd21471edf372b52ff486e8f

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:7e004d00148469cf41d1a26ccb9fe86a513a91dc1280798bf4fc99719d482bb1

Interface hash: sha256:e74a227470ec47b648386f5f405529c34ef9b48eb21324c30920e0f623e08caa

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_report_failure",
  "title": "Report Failure",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_report_failure"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:855236f29dfa7714e6857b3d6d5e2fb6cec9232445c8a17ff5ca734b2f0bbb8f"
}
tooldestructive0.22.0No change observed
plur_session_endplur-ai-plur:tool:plur_session_end
Observed interface and hashes

End a session. BEFORE calling this tool, review the conversation and extract learnings: 1. Corrections the user made ("no, use X not Y") → type: behavioral 2. Preferences stated ("always X", "never Y") → type: behavioral 3. Codebase patterns discovered (naming, structure, conventions) → type: architectural 4. Technical facts learned (API quirks, config, gotchas) → type: procedural 5. Terminology defined or clarified → type: terminological Include at least one engram_suggestion if ANYTHING was learned. An empty suggestions array means nothing worth remembering happened — this should be rare.

Input schema

{
  "properties": {
    "engram_suggestions": {
      "description": "Learnings from this session. Preferred shape is {statement: \"...\", type?: \"...\"}; bare strings are also accepted and treated as the statement. If the whole parameter arrives as one plain string it is ONE suggestion (never split on commas); send several as a JSON array. Review the conversation for corrections, preferences, patterns, and technical facts before calling.",
      "items": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "properties": {
              "scope": {
                "description": "Explicit destination; required when workspace roots disagree.",
                "type": "string"
              },
              "statement": {
                "description": "A concise, reusable assertion. Write it as advice to your future self.",
                "type": "string"
              },
              "type": {
                "enum": [
                  "behavioral",
                  "terminological",
                  "procedural",
                  "architectural"
                ],
                "type": "string"
              }
            },
            "required": [
              "statement"
            ],
            "type": "object"
          }
        ]
      },
      "type": "array"
    },
    "session_id": {
      "description": "Session ID from plur_session_start",
      "type": "string"
    },
    "summary": {
      "description": "What happened in this session (1-3 sentences)",
      "type": "string"
    }
  },
  "required": [
    "summary",
    "engram_suggestions"
  ],
  "type": "object"
}
sha256:eaf2138fc678b7a32bf98106756c862407f23ab239f7b8912458dc6c5fd17291

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:5b66e0efbdd74f4217abf24d1384a2a8651e72e6f5dfb740b6ab0eb06fb789cc

Interface hash: sha256:a7f04aed4551ea298bcdee32f943b09e0195addcd92f1e883374eb8555175479

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_session_end",
  "title": "Session End",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_session_end"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:76e8f6d21eb870ad4f595228c3a0616b9c17d6fc088c657a7dd7d2a32c12bfef"
}
toolwrite0.22.0No change observed
plur_session_startplur-ai-plur:tool:plur_session_start
Observed interface and hashes

Start a session — inject relevant engrams for your task. Call at the beginning of every session.

Input schema

{
  "properties": {
    "default_scope": {
      "description": "Default scope for plur_learn calls this session when no explicit scope is provided. Only set this if you want ALL engrams to route to a specific store. Usually, leave unset and pass scope per-engram based on relevance.",
      "type": "string"
    },
    "tags": {
      "description": "Tags to filter injected engrams",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "task": {
      "description": "What you are working on (triggers engram injection)",
      "type": "string"
    }
  },
  "required": [
    "task"
  ],
  "type": "object"
}
sha256:8be5adc9587d4dbd177d27b983ccc04516a223d7b0c7d7e5ec19c36eef21f7b5

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:12f2520b090b762bc7baa112f88693c83a250a05e1121a0bcd85060fcd2ab769

Interface hash: sha256:3890f5ea37008d7e7a7c9351ee97705b43579ac04453c56744316697c52cb142

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_session_start",
  "title": "Session Start",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_session_start"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:f364595ffbc76349f39350017a56dd1af4b3cce16b09a7dc2b8a477afe3f63f6"
}
toolwrite0.22.0No change observed
plur_statusplur-ai-plur:tool:plur_status
Observed interface and hashes

Return system health — running version, engram count, episode count, pack count, storage root. Optionally filter engram counts by domain prefix and/or creation date.

Input schema

{
  "properties": {
    "check_updates": {
      "description": "If true, ask the npm registry whether a newer PLUR is published and report it as update_available. PLUR also checks once at start; if that check could not connect, PLUR is offline and this answers from the earlier result (update_check: \"offline\") without a new request.",
      "type": "boolean"
    },
    "created_after": {
      "description": "ISO-8601 date (YYYY-MM-DD). Only count engrams learned on or after this date.",
      "type": "string"
    },
    "domain": {
      "description": "Only count engrams whose domain starts with this prefix (e.g. \"meridian\")",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:c3f1a43f93437725ab306a8f8334237d32a2b070163268ed101fb781861e203d

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:60ce3c68d43896c8593ff834092904ac66c8fb9eebcbbc24e277512e838624f0

Interface hash: sha256:56f2492a9d4f64530e1e8972469beaa7ec4590c73c0e2754b07d83d26a45c8d2

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_status",
  "title": "Status",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_status"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "true",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:0afe7929c14174a90c9b1c34421dfe83f3f681f02b17adbc6228f0fff9b59db2"
}
toolread0.22.0No change observed
plur_tensionsplur-ai-plur:tool:plur_tensions
Observed interface and hashes

Tension lifecycle (#181). Default: list persisted tension records (unresolved first). scan:true runs an LLM contradiction scan, persists NEW detections as records, and skips already-recorded pairs. Lifecycle actions: action:"confirm" (real conflict), action:"dismiss" (false positive — pair suppressed from future scans), action:"resolve" + winner:<engram_id> (loser engram retired). Scan requires OPENAI_API_KEY or OPENROUTER_API_KEY env var, or explicit llm_base_url + llm_api_key args.

Input schema

{
  "properties": {
    "action": {
      "description": "Lifecycle action on a persisted tension record (requires id). confirm: mark real. dismiss: false positive, suppress the pair. resolve: pick winner (requires winner), the losing engram is retired.",
      "enum": [
        "confirm",
        "dismiss",
        "resolve"
      ],
      "type": "string"
    },
    "batch_size": {
      "description": "Pairs judged per LLM call in scan mode (default: 5). Set to 1 for sequential single-pair judging.",
      "type": "number"
    },
    "domain": {
      "description": "Filter by domain prefix",
      "type": "string"
    },
    "id": {
      "description": "Tension record id (T-YYYY-MMDD-NNN) for action mode",
      "type": "string"
    },
    "llm_api_key": {
      "description": "API key for the LLM (scan mode)",
      "type": "string"
    },
    "llm_base_url": {
      "description": "OpenAI-compatible API base URL for scan mode (e.g. https://api.openai.com/v1)",
      "type": "string"
    },
    "llm_model": {
      "description": "Model name for scan mode (default: gpt-4o-mini)",
      "type": "string"
    },
    "max_pairs": {
      "description": "Maximum candidate pairs to evaluate in scan mode (default: 50)",
      "type": "number"
    },
    "min_confidence": {
      "description": "Minimum confidence threshold for scan mode (0–1, default: 0.7)",
      "type": "number"
    },
    "persist": {
      "description": "Persist scan detections as tension records (default true). Set false for a dry-run scan that also ignores the recorded-pair suppress list.",
      "type": "boolean"
    },
    "scan": {
      "description": "Run an active contradiction scan using an LLM judge. New detections are persisted as tension records; recorded pairs (any status) are skipped. Requires OPENAI_API_KEY or OPENROUTER_API_KEY env var, or explicit llm_base_url + llm_api_key args.",
      "type": "boolean"
    },
    "scope": {
      "description": "Filter by scope",
      "type": "string"
    },
    "status": {
      "description": "List-mode status filter. Default: unresolved records (detected + confirmed).",
      "enum": [
        "detected",
        "confirmed",
        "dismissed",
        "resolved",
        "all"
      ],
      "type": "string"
    },
    "temporal_discount": {
      "description": "Multiply judge confidence by a days-apart ladder (same day x1.0 ... 15+ days x0.3) in scan mode (#240). Overrides the config default (tensions.temporal_discount, off by default). The judge prompt already carries recorded dates; enable this only when date-aware judging alone leaves too many temporal-evolution false positives.",
      "type": "boolean"
    },
    "winner": {
      "description": "Engram id that wins the tension (action:\"resolve\" only). The other engram is retired.",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:3294cd2ca6560d52fa91ec73b26179e40662c56f10f6454c8ce8ac286f83deb2

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:cf1339e2626e7e784600a494d348d5a8d1c4f552a1cb12d76615c3a2f5d7cc22

Interface hash: sha256:e81334b870f51cd4e366c29ff9810a815ae963387046b2afb9b876961cec6243

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_tensions",
  "title": "Tensions",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_tensions"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:c952617afd42fa2e5ef92e80889f94db587609ab0dd995b2722f6267a3506c8b"
}
tooldestructive0.22.0No change observed
plur_tensions_purgeplur-ai-plur:tool:plur_tensions_purge
Observed interface and hashes

Purge all conflict relations from local engrams — removes accumulated false positives from the legacy tension-detection system

Input schema

{
  "properties": {},
  "type": "object"
}
sha256:3178d649f32f96ea850da50c27c062f5c20cbef86dec2f5af0587dff56ebdb67

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:80c6a5dc54c5fd0160e5b12f1d8e805ebcd60a746e986ffddc44ead7d306166b

Interface hash: sha256:b0477caca81f46816ffc1d02b8a7f8acaf89325978f8a1633e21ba12869893eb

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_tensions_purge",
  "title": "Purge Tensions",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_tensions_purge"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "true",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "unknown"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:fb49d42255bda6d13328f346a23ef7d029c5a2856ef94c3b2717fa1be081ed5e"
}
tooldestructive0.22.0No change observed
plur_validate_metaplur-ai-plur:tool:plur_validate_meta
Observed interface and hashes

Test a meta-engram template against engrams from a new domain — updates confidence and domain_coverage. A meta-engram that fails validation in a third domain is demoted (top → mop) or, below top level, RETIRED.

Input schema

{
  "properties": {
    "llm_api_key": {
      "description": "API key for the LLM",
      "type": "string"
    },
    "llm_base_url": {
      "description": "OpenAI-compatible API base URL",
      "type": "string"
    },
    "llm_model": {
      "description": "Model name (default: gpt-4o-mini)",
      "type": "string"
    },
    "meta_engram_id": {
      "description": "META- engram ID to validate",
      "type": "string"
    },
    "test_domain": {
      "description": "Domain to test against (e.g. medicine)",
      "type": "string"
    }
  },
  "required": [
    "meta_engram_id",
    "test_domain",
    "llm_base_url",
    "llm_api_key"
  ],
  "type": "object"
}
sha256:43023a93a180a5dd78fac0cb4a827628b6b5dc4b535eee27136b4b2e2dc79416

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:75a6dae5e91d73af562fef3a3e340b68731d14ee607f059970e01bbd5ab7d0e4

Interface hash: sha256:5529b9c8e1d85ba11ed3ae62b51f4f1cc4de660a473cf9f083b411a1741c22f8

Other observed Modelara metadata
{
  "id": "mcp:plur-mcp/plur_validate_meta",
  "title": "Validate meta-engram",
  "source": {
    "type": "mcp",
    "server": "plur-mcp",
    "operation": "plur_validate_meta"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:85846efbf16516940a29adb1152ff4793299deed7d3524813f1a971ee169f194"
}
tooldestructive0.22.0No change observed

STATIC COMPARISONS

Release history

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

    Nov 17, 2026· Automated static analysis

  2. 0 added0 removed0 schema0 write0 destructive0 unknown

    Nov 17, 2026· Automated static analysis