memory_explain
Explain a memory's score. Includes a scoremodel block (formula + live per-force breakdown + staleness note) and removalimpact.
How to use it
Project documentation lists memory_explain for the Genesys MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
Install Genesys
claude mcp add genesys -- python -m genesys_memoryOther tools in Genesys (12)
Permanently delete a memory
List core memories, optionally filtered by category
Record a correction: creates a new memory that supersedes an existing one. The old memory is kept (decayed in recall), not deleted.
Recall memories by natural language query (vector + keyword + graph spreading activation). Supports verbosity: "concise" for lightweight payloads.
Filtered vector search by status, category, date (since), last-active date (activesince), or entity. Pass an empty query to enumerate by recency instead (no embedder needed) — with since/activesince this answers "what's new since I last looked" without knowing what to query for.
Get memory system statistics
Store a new memory. Use related for writer-specified typed edges ({id, type}); relatedto is legacy and always creates causedby. Optional category. May return possibleconflicts (heuristic hints).
Walk the causal graph from a node. Returns reachable nodes and the edges of the induced subgraph (source/target/type/weight/createdby) — a superset of the BFS tree, so paths can be reconstructed. Honors edgetypes.
Pin a memory so it's never forgotten
Promote a private memory to org visibility
Set user preferences for core memory categories
Unpin a previously pinned memory