Agentmemory Mcp Tools
Look up the 53 agentmemory MCP tools, core subset, and parameters when wiring persistent agent memory in Claude Code or Cursor.
Overview
agentmemory-mcp-tools is an agent skill most often used in Build (also Operate) that lists all agentmemory MCP tools, parameters, and the eight-tool core subset from the generated registry reference.
Install
npx skills add https://github.com/rohitg00/agentmemory --skill agentmemory-mcp-toolsWhat is this skill?
- Autogenerated reference from tools-registry.ts—regenerate with npm run skills:gen after registry changes
- Documents 53 agentmemory MCP tools with purpose and parameter columns
- Lean core set: 8 tools with --tools core or AGENTMEMORY_TOOLS=core; full set with --tools all (default)
- Covers actions, checkpoints, audit, Claude bridge sync, and broader memory operations
- Tables flag which tools are in the core loadout for smaller agent contexts
- 53 agentmemory MCP tools documented in the generated reference
- 8 tools in the lean core set (--tools core or AGENTMEMORY_TOOLS=core)
- Remaining tools load with --tools all (default)
Adoption & trust: 3 installs on skills.sh; 21.9k GitHub stars; trending (+300% hot-view momentum).
What problem does it solve?
You are wiring agentmemory MCP but cannot tell which of dozens of tools to enable or what each parameter does without reading source code.
Who is it for?
Builders configuring agentmemory MCP in Claude Code or Cursor who need an authoritative tool matrix before automating actions and checkpoints.
Skip if: Learning the house SKILL.md authoring rules (use write-agentmemory-skill) or greenfield brainstorming before you have an agentmemory server attached.
When should I use this skill?
When implementing or debugging agentmemory MCP integrations and you need the current tools-registry parameter matrix.
What do I get? / Deliverables
You pick core versus full tool loadouts and call the right memory_action, checkpoint, audit, or bridge tools with documented parameters during integration and ops debugging.
- Accurate tool name and parameter lookup while coding MCP clients
- Informed choice between eight-tool core and full fifty-three-tool sets
- Cross-check against generated AUTOGEN:tools block in the repo
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
The registry documents MCP integrations you connect during product and agent assembly, even though memory tooling also matters once you operate live agents. Tool names, core flags, and parameters are integration surface area for the agentmemory MCP server, not end-user UI work.
Where it fits
Enable --tools core first, then expand to all after confirming action dependency tools are required.
Verify memory_action_update status transitions unblock dependent actions using the documented parameters.
Use memory_audit limits during an incident to trace recent memory mutations.
How it compares
Use this generated MCP registry instead of guessing tool names from chat context when the server exposes dozens of memory_* endpoints.
Common Questions / FAQ
Who is agentmemory-mcp-tools for?
Solo developers and agent integrators who run the agentmemory MCP server and need a complete, parameter-level tool list while coding automations.
When should I use agentmemory-mcp-tools?
During Build integrations while selecting core versus all tools; during Ship testing when validating action/checkpoint flows; and in Operate monitoring when tracing audit or bridge sync calls.
Is agentmemory-mcp-tools safe to install?
The reference describes powerful memory and action tools that can mutate project state—scope MCP permissions carefully and review the Security Audits panel on this Prism page.
Workflow Chain
Then invoke: write agentmemory skill
SKILL.md
READMESKILL.md - Agentmemory Mcp Tools
# agentmemory MCP tools reference Generated from `src/mcp/tools-registry.ts`. Do not edit the block below by hand; run `npm run skills:gen` after changing the registry. <!-- AUTOGEN:tools START - generated by scripts/skills/generate.ts, do not edit by hand --> agentmemory exposes 53 MCP tools. 8 are in the lean core set (`--tools core` or `AGENTMEMORY_TOOLS=core`); the rest load with `--tools all` (default). | Tool | Core | Parameters | Purpose | | --- | --- | --- | --- | | `memory_action_create` | | `title`*: string, `description`: string, `priority`: number, `project`: string, `tags`: string, `parentId`: string, `requires`: string | Create an actionable work item with typed dependencies. Actions track what agents need to do and how work items relate to each other. | | `memory_action_update` | | `actionId`*: string, `status`: string, `result`: string, `priority`: number | Update an action's status, priority, or details. Set status to 'done' to complete it and unblock dependent actions. | | `memory_audit` | | `operation`: string, `limit`: number | View the audit trail of memory operations. | | `memory_checkpoint` | | `operation`*: string, `name`: string, `checkpointId`: string, `status`: string, `type`: string, `linkedActionIds`: string | Create or resolve an external checkpoint (CI result, approval, deploy status) that gates action progress. | | `memory_claude_bridge_sync` | | `direction`*: string | Sync memory state to/from Claude Code's native MEMORY.md file. | | `memory_commit_lookup` | | `sha`*: string | Look up the agent session(s) that produced a specific git commit, given its SHA. Returns the commit metadata and linked sessions. | | `memory_commits` | | `branch`: string, `repo`: string, `limit`: number | List recent commits linked to agent sessions, optionally filtered by branch or repo. | | `memory_compress_file` | | `filePath`*: string | Compress a markdown file to reduce token usage while preserving headings, URLs, and code blocks. Creates a .original.md backup before writing. | | `memory_consolidate` | yes | `tier`: string | Run the 4-tier memory consolidation pipeline (working -> episodic -> semantic -> procedural). | | `memory_crystallize` | | `actionIds`*: string, `project`: string, `sessionId`: string | Compress completed action chains into compact crystal digests using LLM summarization. Extracts narrative, key outcomes, files affected, and lessons. | | `memory_diagnose` | yes | `categories`: string | Run health checks across all subsystems (actions, leases, sentinels, sketches, signals, sessions, memories, mesh). Identifies stuck, orphaned, and inconsistent state. | | `memory_export` | | none | Export all memory data as JSON. | | `memory_facet_query` | | `matchAll`: string, `matchAny`: string, `targetType`: string | Query targets by facet tags with AND/OR logic. Find all actions tagged priority:urgent AND team:backend. | | `memory_facet_tag` | | `targetId`*: string, `targetType`*: string, `dimension`*: string, `value`*: string | Attach a structured tag (dimension:value) to an action, memory, or observation for multi-dimensional categorization. | | `memory_file_history` | | `files`*: string, `sessionId`: string | Get past observations about specific files. | | `memory_frontier` | | `project`: string, `agentId`: string, `limit`: number | Get all unblocked actions ranked by priority and urgency. Returns the frontier of actionable work with no unsatisfied dependencies. | | `memory_governance_delete` | | `memoryIds`*: string, `reason`: string | Delete specific memories with audit trail. | | `memory_graph_query` | | `startNodeId`: string, `nodeType`: string, `maxDepth`: number, `query`: string | Query the knowledge graph for entities and relationships. | | `memory_heal` | | `categories`: string, `dryRun`: string | Auto-fix all fixable issues found by diagnostics. Unblocks stuck actions, expires stale leases, cleans up orphaned data. | | `memory_insight_list` | | `project`: string, `minConfidenc