MARM MCP is an intelligent persistent memory system for AI agents that provides long-term recall, session continuity, and reliable conversation history, allowing LLMs to maintain context across interactions.
From the registry: Universal MCP Server with advanced AI memory capabilities and semantic search.
$ docker pull lyellr88/marm-mcp-server:latest$ docker run -d --name marm-mcp-server -p 8001:8001 -v ~/.marm:/home/marm/.marm lyellr88/marm-mcp-server:latestPlease install the `marm-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Pull Docker image** — Pull the MARM MCP server Docker image Run: `docker pull lyellr88/marm-mcp-server:latest`
- **Run Docker container** — Run the container exposing port 8001 Run: `docker run -d --name marm-mcp-server -p 8001:8001 -v ~/.marm:/home/marm/.marm lyellr88/marm-mcp-server:latest`
Canonical MCP server config (HTTP transport):
- url: `http://localhost:8001/mcp`
Note: Runs as local HTTP server via Docker (recommended) or `pip install marm-mcp-server`. STDIO transport also supported via server_stdio.py. Optional local dev OAuth credentials included.
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.CLIENT_IDrequiredLocal OAuth 2.0 client ID for development.CLIENT_SECRETrequiredLocal OAuth 2.0 client secret for development.AI Agents Framework with Self Reflection and MCP support