Cuba-Memorys is a Model Context Protocol (MCP) server that provides AI coding assistants with long-term memory through a knowledge graph and advanced algorithms for memory management and retrieval.
From the registry: Persistent memory for AI agents. 19 tools, Hebbian learning, RRF search, knowledge graph.

$ npm install -g cuba-memorysPlease install the `cuba-memorys` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install globally** — Install via npm or pip. Run: `npm install -g cuba-memorys`
- **Install Docker** — Docker must be running. PostgreSQL+pgvector is auto-provisioned on first run. (https://docs.docker.com/get-docker/)
Canonical MCP server config (stdio transport):
- command: `cuba-memorys`
- args: []
- optional environment variables:
- `DATABASE_URL`: Custom PostgreSQL URL (with pgvector). If omitted, Docker auto-provisions one.
Note: Zero-config: auto-provisions PostgreSQL via Docker on first run.
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.DATABASE_URLCustom PostgreSQL connection string if not using the auto-provisioned database.AI Agents Framework with Self Reflection and MCP support