mcpField
A
agentmemory-mcp-tools

agentmemory-mcp-tools

github.com/rohitg00Agent workflows30.0k11.0k installsUpdated today
Repository

About agentmemory-mcp-tools

agentmemory-mcp-tools is a skill that documents the MCP tools exposed by agentmemory. It helps agents select memory capture, retrieval, session, graph, slot, and governance operations using their documented schemas.

Key features

  1. 01Index MCP tool families and schemas
  2. 02Save and search memory
  3. 03Retrieve sessions, files, and timelines
  4. 04Query knowledge graphs and structured slots
  5. 05Run governance and health operations

Use cases

  1. 01Save an insight for later retrieval
  2. 02Search memory with a focused query
  3. 03Inspect sessions or memory relationships

MCP support

The skill describes tools provided by an agentmemory MCP server, including operations for memory capture, retrieval, sessions, knowledge graphs, structured slots, governance, and health.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/rohitg00/agentmemory --skill agentmemory-mcp-tools

After installing, type/agentmemory-mcp-toolsin Claude Code to confirm it loaded.

Bundled filesREFERENCE.mdTROUBLESHOOTING.md

Details

From the project README

This skill indexes agentmemory's MCP tools. Use the connected server's tool inventory and schemas; a native memory provider may expose a smaller set under different names. Hermes and OpenClaw skills that need the full surface require a separate MCP connection to the running daemon. For Pi and OMP, connect with --with-mcp to enable the broader workflows. Pi exposes MCP names with an mcp__agentmemory__ prefix; OMP exposes MCP operations as xd://mcp__agentmemory_<tool> devices through its write tool.

Quick start

Save then recall:

  1. memory_save with content (the insight), concepts (comma-separated keywords), files (comma-separated paths).
  2. memory_smart_search with query, limit, and targetLayer: "memory" to retrieve saved knowledge later. Omit targetLayer to also search captured observations. This runs hybrid BM25 plus vector plus graph-expanded search.

Tool families

  • Capture: memory_save, memory_compress_file. Automatic observations use native hooks or POST /agentmemory/observe, not an MCP observation tool.
  • Retrieve: memory_smart_search, memory_recall, memory_file_history, memory_timeline, memory_vision_search.
  • Sessions and commits: memory_sessions, memory_commits, memory_commit_lookup.
  • Knowledge and graph: memory_lesson_save, memory_lesson_recall, memory_graph_query, memory_relations, memory_patterns, memory_crystallize.
  • Structured slots: memory_slot_create, memory_slot_append, memory_slot_get, memory_slot_list, memory_slot_replace, memory_slot_delete.
  • Governance and health: memory_governance_delete, memory_audit, memory_verify, memory_heal, memory_diagnose.

Workflow

  1. Pick the narrowest tool for the task. Prefer memory_smart_search for open recall, memory_recall when you already have a focused query, memory_sessions for session listings.
  2. Look up exact parameter names and which are required in REFERENCE.md before calling.
  3. Pass only documented fields. REST handlers whitelist fields and drop unknown ones.
  4. For budgeted memory_recall, distinguish matched_count: 0 from excluded_by_budget > 0. Expand clipped or omitted IDs with memory_smart_search and expandIds, preserving the same scope filters.

See also

  • agentmemory-rest-api for the HTTP equivalents.
  • agentmemory-config for tool-visibility and feature flags.
  • The user-invocable action skills (remember, recall, recap, handoff, forget) wrap the most common tools.

Reference

Full tool table with parameters and the core-set marking lives in REFERENCE.md, generated from source so it never drifts.

Comments

Markdown supported