MCP tools - agentmemory

Descriptions below are the registry text the agent sees (src/mcp/tools-registry.ts). AGENTMEMORY_TOOLS=core trims the surface to 8 essentials: memory_save, memory_recall, memory_consolidate, memory_smart_search, memory_sessions, memory_diagnose, memory_lesson_save, memory_reflect.

Recall and save

Tool	Description
`memory_recall`	Search past session observations for relevant context. Use when you need to recall what happened in previous sessions, find past decisions, or look up how a file was modified before.
`memory_smart_search`	Hybrid semantic+keyword search with progressive disclosure.
`memory_save`	Explicitly save an important insight, decision, or pattern to long-term memory.
`memory_timeline`	Chronological observations around an anchor point.
`memory_file_history`	Get past observations about specific files.
`memory_patterns`	Detect recurring patterns across sessions.
`memory_vision_search`	Cross-modal image search via CLIP embeddings. Pass queryText to find screenshots matching a description, or queryImageBase64/queryImageRef to find similar images. Requires AGENTMEMORY_IMAGE_EMBEDDINGS=true.
`memory_compress_file`	Compress a markdown file to reduce token usage while preserving headings, URLs, and code blocks. Creates a .original.md backup before writing.
`memory_verify`	Verify a memory or observation by tracing its citation chain back to source observations and session context. Returns provenance information including confidence scores.
`memory_consolidate`	Run the 4-tier memory consolidation pipeline (working -> episodic -> semantic -> procedural).
`memory_slot_list`	List all memory slots (pinned + project + global). Slots are editable, size-limited memory units the agent can read and modify across sessions.
`memory_slot_get`	Read a single slot by label.
`memory_slot_create`	Create a new slot. Reject if a slot with the same label already exists.
`memory_slot_append`	Append text to an existing slot. Fails with 413 if the append would exceed the slot’s sizeLimit; the agent must compact via memory_slot_replace first.
`memory_slot_replace`	Replace slot content in place. Fails if content exceeds sizeLimit.
`memory_slot_delete`	Delete a slot. Seeded default slots can be deleted unless marked readOnly.

Lessons and insights

Tool	Description
`memory_lesson_save`	Save a lesson learned from this session. Lessons have confidence scores that strengthen when reinforced and decay when not used. Duplicate content auto-strengthens the existing lesson.
`memory_lesson_recall`	Search lessons by query. Returns lessons sorted by confidence and recency. Use to check what the agent has learned before making decisions.
`memory_lesson_delete`	Soft-delete a lesson by id. Deleted lessons are excluded from recall and list; re-saving the same content creates a fresh lesson.
`memory_reflect`	Traverse the knowledge graph, group related memories by concept clusters, and synthesize higher-order insights via LLM. Returns new and reinforced insights.
`memory_insight_list`	List synthesized insights: higher-order observations derived from patterns across memories, lessons, and crystals.

Actions and coordination

Tool	Description
`memory_action_create`	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`	Update an action’s status, priority, or details. Set status to ‘done’ to complete it and unblock dependent actions.
`memory_frontier`	Get all unblocked actions ranked by priority and urgency. Returns the frontier of actionable work with no unsatisfied dependencies.
`memory_next`	Get the single most important next action to work on. Combines dependency resolution, priority, and recency into a score.
`memory_lease`	Acquire, release, or renew an exclusive lease on an action. Prevents multiple agents from working on the same thing.
`memory_routine_run`	Instantiate a frozen workflow routine, creating actions for each step with proper dependencies.
`memory_signal_send`	Send a message to another agent or broadcast. Supports threading, typed messages, and TTL expiration.
`memory_signal_read`	Read messages for an agent. Marks delivered messages as read.
`memory_checkpoint`	Create or resolve an external checkpoint (CI result, approval, deploy status) that gates action progress.
`memory_sentinel_create`	Create an event-driven sentinel that watches for conditions (webhook, timer, threshold, pattern, approval) and auto-unblocks gated actions when triggered.
`memory_sentinel_trigger`	Externally fire a sentinel, providing an optional result payload. Unblocks any gated actions.
`memory_sketch_create`	Create an ephemeral action graph for exploratory work. Auto-expires after TTL. Can be promoted to permanent actions or discarded.
`memory_sketch_promote`	Promote a sketch’s ephemeral actions to permanent actions. Makes the exploratory work official.
`memory_facet_tag`	Attach a structured tag (dimension:value) to an action, memory, or observation for multi-dimensional categorization.
`memory_facet_query`	Query targets by facet tags with AND/OR logic. Find all actions tagged priority:urgent AND team:backend.

Crystals and export

Tool	Description
`memory_crystallize`	Compress completed action chains into compact crystal digests using LLM summarization. Extracts narrative, key outcomes, files affected, and lessons.
`memory_export`	Export all memory data as JSON.
`memory_obsidian_export`	Export memories, lessons, and crystals as Obsidian-compatible Markdown files with YAML frontmatter and wikilinks for graph view.
`memory_claude_bridge_sync`	Sync memory state to/from Claude Code’s native MEMORY.md file.
`memory_snapshot_create`	Create a git-versioned snapshot of current memory state.

Graph

Tool	Description
`memory_graph_query`	Query the knowledge graph for entities and relationships.
`memory_relations`	Query the memory relationship graph.

Team and mesh

Tool	Description
`memory_team_share`	Share a memory or observation with team members.
`memory_team_feed`	Get recent shared items from all team members.
`memory_mesh_sync`	Sync memories and actions with peer agentmemory instances for multi-agent collaboration.

Governance and health

Tool	Description
`memory_governance_delete`	Delete specific memories with audit trail.
`memory_audit`	View the audit trail of memory operations.
`memory_diagnose`	Run health checks across all subsystems (actions, leases, sentinels, sketches, signals, sessions, memories, mesh). Identifies stuck, orphaned, and inconsistent state.
`memory_heal`	Auto-fix all fixable issues found by diagnostics. Unblocks stuck actions, expires stale leases, cleans up orphaned data.

Sessions and profile

Tool	Description
`memory_sessions`	List recent sessions with their status and observation counts.
`memory_profile`	User/project profile with top concepts and file patterns.
`memory_commit_lookup`	Look up the agent session(s) that produced a specific git commit, given its SHA. Returns the commit metadata and linked sessions.
`memory_commits`	List recent commits linked to agent sessions, optionally filtered by branch or repo.

Last modified on August 15, 2026