Get the current version of the Memory MCP server and configuration.

Set the active project. Subsequent tools use it by default.

Initialize a new project namespace (creates DuckDB + registers it).

List all registered projects.

Get detailed info for a project.

Store a new memory with auto-embedding, summary, entity extraction, and TTL.

Semantic search with composite relevance scoring.

Recall a specific memory by ID or exact title.

Update an existing memory. Re-embeds if title/content changed.

Soft-delete (archive) or hard-delete a memory.

List memories with filtering, sorting, and pagination.

Get the full audit trail for a memory.

Get all mandatory and forbidden rules (direct SQL, cached).

Start a session. Loads rules, last summary, sprint goals, recent decisions.

End a session and store its summary.

Attach an existing project directory. Auto-activates on success.

Move the project's DB into the project directory for git sharing.

Sync a portable DB after git pull. Auto-activates on success.

Export all active memories to human-readable .md files.

Import memories from exported .md files.

Current embedding model + available presets.

Switch embedding model between 'english' and 'multilingual' presets.

Re-embed all active memories with the current model.

Check if a newer version of the Memory MCP server is available.

Queries GitHub Releases first, falls back to git commit comparison. Does NOT modify anything - it only reports. Returns step-by-step update instructions when a new version is available.