Memory MCP is a SQLite-backed server that provides persistent memory storage, full-text retrieval, and relationship graph traversal for MCP-enabled assistants.
From the registry: SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.
Please install the `memory-mcp-j0hanz` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js >=24** — Requires Node.js 24+ with SQLite FTS5 (https://nodejs.org/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@j0hanz/memory-mcp@latest"]
- optional environment variables:
- `MEMORY_DB_PATH`: SQLite database file path (example: `memory_db/memory.db`)
- `RECALL_MAX_FRONTIER_SIZE`: Max BFS frontier nodes per hop (example: `1000`)
- `RECALL_MAX_EDGE_ROWS`: Max relationship rows per traversal (example: `5000`)
- `RECALL_MAX_VISITED_NODES`: Max visited nodes per traversal (example: `5000`)
Note: SQLite-backed. stdio only. Also available as Docker image.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MEMORY_DB_PATHrequiredPath to the SQLite database for memory storage.MCP server for interacting with the Supabase platform