Remembra — AI Memory Layer

Please install the `remembra` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Remembra server running** — A Remembra backend instance must be running locally or remotely. Quickstart: curl -sSL https://raw.githubusercontent.com/remembra-ai/remembra/main/quickstart.sh | bash Run: `curl -sSL https://raw.githubusercontent.com/remembra-ai/remembra/main/quickstart.sh | bash` (https://docs.remembra.dev/getting-started/docker/)
- **Docker (for quickstart)** — Docker is needed to run the Remembra backend with Qdrant and Ollama via docker-compose Run: `docker --version` (https://docs.docker.com/get-docker/)
- **Python with remembra package** — Install the remembra Python package which includes the MCP server binary remembra-mcp Run: `pip install remembra[mcp]` (https://pypi.org/project/remembra/)

Canonical MCP server config (stdio transport):
- command: `remembra-mcp`
- args: []
- required environment variables:
  - `REMEMBRA_URL`: URL of your running Remembra backend server (example: `http://localhost:8787`)
- optional environment variables:
  - `REMEMBRA_USER_ID`: User ID for memory isolation. Defaults to 'default'. (example: `default`)

Note: Self-hosted AI memory layer. Requires a running Remembra backend (Qdrant + SQLite). Quickstart spins up all dependencies via Docker. Alternative: claude mcp add remembra -e REMEMBRA_URL=http://localhost:8787 -- remembra-mcp. 11 MCP tools including store_memory, recall_memories, update_memory, forget_memories, search_entities, timeline, etc.

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.