Store knowledge atomically — entity + observations + relations in ONE call. PRIMARY TOOL for storing new knowledge. Prevents orphan entities. AUTO-BLOCKS if similar entity exists (>80% match). Use force=True to override.

Create relations (edges) between entities. Every entity should have at least one relation. Use specific types: uses, implements, part_of, depends_on, alternative_to, decided_by, affects. Avoid generic 'related_to' when a specific type fits.

Add atomic facts to existing entities. One fact per observation — don't dump paragraphs. Use prefixes: 'Gotcha: ...', 'Warning: ...', 'Status: ...', 'Source: ...'. For relations, use create_relations instead of 'X is related to Y' observations.

Delete entities by name (cascades to relations)

Delete specific relations

Delete specific observations from entities

PRIMARY RETRIEVAL TOOL. Get relevant context with automatic token management. Use focus=['EntityName'] to get full details on specific entities. shallow=quick summary, medium=semantic search+neighbors, deep=full exploration.

Get graph state at a specific point in time (event rewind)

Show what changed between two points in time

Get the history of all changes to an entity

Set explicit importance weight for a relation

Get an entity's strongest connections by edge weight

Get relations below a weight threshold (pruning candidates)

Get oriented with this knowledge graph. Call at session start.

Signal session start and get initial context. Returns quick_start guide with tool usage. IMPORTANT: If memory is empty, ask user whether to use project-local or global memory scope.

Signal session end, optionally save summary

Find entities with similar names (potential duplicates). Use before creating to check for existing entities. Returns similarity scores — consider merging if >0.85.

Find entities with no relations (likely incomplete). Orphans should be connected, merged into another entity, or deleted.

Merge source entity into target. Source's observations and relations move to target, then source is deleted. Use to consolidate duplicates (e.g., merge 'ReactJS' into 'React').

Assess knowledge graph quality. Returns: orphan count, potential duplicates, overloaded entities, weak relations. Run periodically to maintain graph hygiene. Use full=true for deep duplicate detection (slower).

Suggest potential relations for an entity based on semantic similarity and co-occurrence. Useful for connecting newly created entities or discovering missing links.

Clear ALL entities and relations from the graph. Use sparingly! For graphs with >10 entities: requires reason AND confirm_token. Event-sourced: can rewind to before clear with get_state_at(timestamp).

Reload graph state from mnemograph.db on disk. Use after: git operations (checkout, restore), external edits to mnemograph.db, or any time MCP server seems out of sync.

Rewind graph to a previous state using git. Fast undo, audit trail in git only. For audit-preserving restore, use restore_state_at() instead.

Restore graph to state at a specific timestamp. Emits clear + recreate events — full audit trail preserved. Use get_state_at() first to preview what will be restored.

List all memory branches. Branches are filtered views of the knowledge graph. Main branch sees everything; other branches see filtered subsets.

Get the name and details of the currently active branch.

Create a new branch with seed entities. Uses BFS to expand from seeds to N-hop neighbors. Branch names follow format: / where type is project|feature|domain|spike|archive.

Switch to a different branch. Changes what entities/relations are visible in queries. Use 'main' to see everything.

Add entities to the current branch. Only works on non-main branches. Optionally includes relations between added entities.

Show differences between two branches. Returns entities and relations that are only in one branch vs the other, plus what's common to both.