agentmemory-mcp-tools
rohitg00/agentmemory
Index of agentmemory MCP tools for memory capture, retrieval, and knowledge management.
What is agentmemory-mcp-tools?
Reference skill that maps every agentmemory MCP tool, its purpose, and parameters. Use this when choosing which memory tool to call, clarifying tool names or arguments, or understanding agentmemory's full MCP capability set.
- Maps all agentmemory MCP tools across six families: capture, retrieve, sessions, knowledge/graph, structured slots, and governance
- Provides exact parameter names and requirements for each tool before calling
- Guides tool selection by narrowness—preferring smart_search for open recall, recall for focused queries, sessions for listings
- Explains hybrid search capabilities (BM25 + vector + graph-expanded) via memory_smart_search
- Documents tool families including memory_save, memory_observe, memory_lesson_save, memory_slot_* operations, and governance tools
How to install agentmemory-mcp-tools
npx skills add https://github.com/rohitg00/agentmemory --skill agentmemory-mcp-toolsHow to use agentmemory-mcp-tools
- 1.Install the skill via: npx skills add https://github.com/rohitg00/agentmemory --skill agentmemory-mcp-tools
- 2.When uncertain which memory tool to call, consult this skill's tool families (capture, retrieve, sessions, knowledge, slots, governance)
- 3.Before calling any tool, look up exact parameter names and required fields in REFERENCE.md (generated from source)
- 4.Pass only documented fields to tools; REST handlers whitelist and drop unknown ones
- 5.Prefer the narrowest tool for the task: memory_smart_search for open recall, memory_recall for focused queries, memory_sessions for session listings
Use cases
- Deciding which memory tool to use when an agent needs to save insights with concepts and file paths
- Looking up exact parameter names and required fields before calling a memory tool via MCP
- Understanding what agentmemory can do across capture, retrieval, knowledge graphs, and structured storage
- Debugging tool calls by checking documented fields and REST handler whitelisting rules
- Choosing between memory_smart_search (hybrid), memory_recall (focused), or memory_sessions (listings) for different retrieval patterns
- AI agents (Claude Code, Cursor) integrating agentmemory via MCP
- Developers building memory-augmented workflows who need tool reference
- Teams using agentmemory for session tracking, knowledge crystallization, or audit trails
agentmemory-mcp-tools FAQ
memory_smart_search runs hybrid BM25 + vector + graph-expanded search for open-ended queries; memory_recall is for focused, already-narrowed queries.
REFERENCE.md contains the full tool table with parameters, generated from source so it never drifts.
No. REST handlers whitelist documented fields and drop unknown ones. Only pass fields listed in REFERENCE.md.
Capture (save, observe, compress), Retrieve (smart_search, recall, file_history, timeline, vision_search), Sessions/Commits, Knowledge/Graph, Structured Slots, and Governance/Health.
No. This is a reference skill for agents to consult when choosing or calling agentmemory MCP tools.
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; use when MCP is unavailable or integration requires 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 memories from agentmemory with explicit user confirmation.
handoff
Resume the most recent agent session for your project, picking up from any unanswered question.
lesson
Save confidence-weighted behavioral rules that resurface before similar work.