agentmemory-mcp-tools
rohitg00/agentmemory
Index of agentmemory MCP tools: which tool to call, exact parameters, and when to use each.
What is agentmemory-mcp-tools?
This skill maps every agentmemory MCP tool—capture, retrieve, sessions, knowledge graph, slots, and governance—with their parameters and use cases. Use it when choosing which memory tool to call, clarifying argument names, or explaining what agentmemory can do via MCP.
- Index all agentmemory MCP tools across six families: capture, retrieve, sessions/commits, knowledge/graph, structured slots, and governance
- Specify exact parameter names and which are required for each tool
- Guide tool selection by narrowing to the most specific tool for each task
- Reference hybrid search capabilities (BM25, vector, graph-expanded) in memory_smart_search
- Document tool families and their primary use cases
How to install agentmemory-mcp-tools
npx skills add https://github.com/rohitg00/agentmemory --skill agentmemory-mcp-toolsHow to use agentmemory-mcp-tools
- 1.Identify the task category: capture (save/observe/compress), retrieve (search/recall/timeline), sessions, knowledge/graph, slots, or governance
- 2.Pick the narrowest tool that fits your task
- 3.Reference REFERENCE.md (generated from source) for exact parameter names and required fields
- 4.Pass only documented fields; REST handlers whitelist and drop unknown ones
- 5.Call the selected tool with correct parameters
Use cases
- Choose between memory_smart_search (open recall), memory_recall (focused query), or memory_sessions (session listings)
- Look up required parameters before calling a tool to avoid whitelist rejection
- Understand when to use memory_save with concepts and files versus memory_observe for flow capture
- Determine which retrieval tool fits: timeline, file history, vision search, or graph query
- Answer user questions about agentmemory's full MCP capability set
- Developers building agents that call agentmemory MCP tools
- Agents needing to select the right memory tool for a given task
- Teams documenting or auditing which memory operations are available
agentmemory-mcp-tools FAQ
memory_smart_search runs hybrid BM25 plus vector plus graph-expanded search for open-ended queries. memory_recall is for when you already have a focused query and want faster, more targeted retrieval.
Use memory_save with content (the insight), concepts (comma-separated keywords), and files (comma-separated paths). For capturing workflows or flows, use memory_observe instead.
REFERENCE.md contains the full tool table with parameters and core-set marking. It is generated from source so it never drifts.
No. REST handlers whitelist fields and drop unknown ones. Only pass documented fields from REFERENCE.md.
Use memory_governance_delete, memory_audit, memory_verify, memory_heal, and memory_diagnose for managing memory integrity and access control.
Full instructions (SKILL.md)
Source of truth, from rohitg00/agentmemory.
name: agentmemory-mcp-tools description: Map of every agentmemory MCP tool, what each does, and its parameters. Use when choosing which memory tool to call, when a tool name or argument is unclear, or when answering what agentmemory can do via MCP. user-invocable: false
agentmemory exposes its full capability set as MCP tools. This skill is the index: it tells you which tool to reach for and where to find exact parameters.
Quick start
Save then recall:
memory_savewithcontent(the insight),concepts(comma-separated keywords),files(comma-separated paths).memory_smart_searchwithqueryandlimitto retrieve it later. This runs hybrid BM25 plus vector plus graph-expanded search.
Tool families
- Capture:
memory_save,memory_observeflows,memory_compress_file. - 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
- Pick the narrowest tool for the task. Prefer
memory_smart_searchfor open recall,memory_recallwhen you already have a focused query,memory_sessionsfor session listings. - Look up exact parameter names and which are required in REFERENCE.md before calling.
- Pass only documented fields. REST handlers whitelist fields and drop unknown ones.
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.
Related skills
More from rohitg00/agentmemory and the wider catalog.
agentmemory-rest-api
HTTP REST API for agentmemory memory server—save and recall agent knowledge over HTTP.
commit-context
Trace code back to the agent session that created it—answer 'why is this here' and 'what was the agent doing'.
commit-history
List recent git commits linked to agent sessions, filtered by branch or repo.
forget
Delete specific observations from agentmemory with explicit user confirmation.
handoff
Resume the most recent agent session for your project, picking up from any unanswered question.
recall
Search past observations and learnings using hybrid BM25, vector, and graph search.