Skip to content
MCP server

MemoCat — Shared AI Memory

One shared, persistent memory across AI agents and systems, with semantic recall and…

Runs locallyStatus and history
Install
Pricing
Open source
Runs
Locally
Version
0.4.3
Listing updated
4 days ago

About MemoCat — Shared AI Memory

MemoCat — Shared AI Memory is an open-source MCP server for knowledge and memory. It runs locally on your machine and is started by your AI client.

One shared, persistent memory across AI agents and systems, with semantic recall and live updates.

Install

Run in a terminal

claude mcp add memocat-mcp --env MONTYCAT_URI='<MONTYCAT_URI>' -- uvx memocat-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "memocat-mcp": {
      "command": "uvx",
      "args": [
        "memocat-mcp"
      ],
      "env": {
        "MONTYCAT_URI": "<MONTYCAT_URI>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "memocat-mcp": {
      "command": "uvx",
      "args": [
        "memocat-mcp"
      ],
      "env": {
        "MONTYCAT_URI": "<MONTYCAT_URI>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "memocat-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "memocat-mcp"
      ],
      "env": {
        "MONTYCAT_URI": "<MONTYCAT_URI>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "memocat-mcp": {
      "command": "uvx",
      "args": [
        "memocat-mcp"
      ],
      "env": {
        "MONTYCAT_URI": "<MONTYCAT_URI>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "memocat-mcp": {
      "command": "uvx",
      "args": [
        "memocat-mcp"
      ],
      "env": {
        "MONTYCAT_URI": "<MONTYCAT_URI>"
      }
    }
  }
}

Configuration

  • MONTYCAT_URIOptional Montycat engine URI: montycat://user:password@host:port/store
  • MONTYCAT_TLSSet to true when connecting to a TLS-enabled remote Montycat engine
  • MONTYCAT_URIOptional Montycat engine URI: montycat://user:password@host:port/store
  • MONTYCAT_TLSSet to true when connecting to a TLS-enabled remote Montycat engine

Pricing

Open source

MemoCat — Shared AI Memory FAQ

Is MemoCat — Shared AI Memory free?

Yes. MemoCat — Shared AI Memory is open source, so you can use and self-host it for free.

How do I add MemoCat — Shared AI Memory to Claude Code?

Run this command in your terminal: claude mcp add memocat-mcp --env MONTYCAT_URI='<MONTYCAT_URI>' -- uvx memocat-mcp

What are the best alternatives to MemoCat — Shared AI Memory?

The closest alternatives to MemoCat — Shared AI Memory are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

Alternatives to MemoCat — Shared AI Memory

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  2. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  3. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  4. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  5. note1

    MCP server

    MCP server giving AI assistants search and summaries across your note1 meetings

    • 4 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Productivity