mnema

Official

Overview Schema Source Related Servers Discussions Admin

Capture a memory

capture_memory

Records a point-in-time fact or decision in an append-only chain, attributed to the agent and session, with optional public, private, or global scope.

Instructions

Record a point-in-time fact into the mnema chain, attributed to this agent and pinned to the current session. Optionally pick the scope it lands in: public (team-visible), private (this machine, this project), or global (personal, cross-project); omitted, it follows the session default (private for an agent in a project, global outside one). Optionally pick the project it lands in, when the workspace holds more than one. The reply says which tree it landed in. RECORDING IS PERMANENT: mnema is append-only and nothing deletes a fact. A record in the public scope is committed to the repository and reaches every machine that clones it (published, if that repository is public). So do NOT record credentials here. Values in a recognized format (cloud keys, API tokens, private keys, a password inside a URL) are replaced with a typed placeholder before anything is written and the reply says what was replaced, but a format mnema does not recognize is written verbatim and cannot be taken back. Do not record personal data either: an email address is replaced with and reported, and the mnid already says who wrote. Each text field holds at most 65536 bytes; a longer one is refused, not truncated.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "content": "<content>"
    },
    "name": "capture_memory"
  }
}

Input Schema

Name	Required	Description
`scope`	No	Where the memory lands; overrides the session default.
`content`	Yes	The memory to record.
`project`	No	Which project of this workspace the fact belongs to: its absolute path, as this server gave it; a bare name is refused. Omitted, it lands in the project this session resolved to (the one `bootstrap` names). Pass it whenever the work being recorded happened in a different project of this workspace.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well past the annotations: append-only permanence, no deletion path, public-scope commits reaching every clone, secret/personal-data redaction with reporting, and a 65536-byte hard cap that refuses rather than truncates. The one tension is irreversible, potentially repo-publishing writes under destructiveHint=false and idempotentHint=false — the description explains the immutability, which arguably justifies the flag, but an agent may still misread the safety profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and scope selection are front-loaded, then the permanence warning follows in caps, which is the right ordering for a write tool. It runs long — the redaction paragraph is dense — but nearly every clause carries decision-relevant information, so the sprawl is mostly justified.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter write tool with no output schema, the description covers the return signal ("the reply says which tree it landed in," and reports what was redacted), the default resolution behavior, and the irreversible failure modes. Nothing an agent needs before calling it is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, yet the description still earns its keep: it defines each scope value (public = team-visible, private = this machine/project, global = personal cross-project) and spells out the resolution order when scope or project is omitted. The project parameter's "absolute path, bare name is refused" constraint and the size/redaction behavior of content add meaning the schema does not carry.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Record a point-in-time fact into the mnema chain, attributed to this agent and pinned to the current session" gives a concrete verb, resource, and provenance model, which distinguishes it from the record_decision / record_observation / record_handoff siblings by implication (a bare fact, not a structured artifact). It stops short of naming which sibling to prefer for decisions or observations, so it is clear but not fully differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Offers decision rules rather than just context: choose the scope for visibility, pass project "whenever the work being recorded happened in a different project of this workspace," and avoid credentials and personal data. The missing piece is guidance on when to use this versus the other record_* tools, which the description never addresses.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.