Montycat MCP - Shared Memory for AI Agents

Montycat MCP - Shared Memory for AI Agents is a local MCP server: Shared, persistent memory for AI agents, with semantic recall and live updates. Install it from pypi as montycat-mcp.

Claude CodeCodexAntigravity

commandprompt

Terminal

claude mcp add montycat-mcp -e MONTYCAT_URI=... -e MONTYCAT_TLS=... -e MONTYCAT_TLS_CERTIFICATE_PATH=... -e MONTYCAT_TLS_VERIFY=... -e MONTYCAT_TLS_CERTIFICATE_FINGERPRINT=... -- uvx montycat-mcp

Run in your project folder. Add --scope user to use it everywhere.

Add to claude_desktop_config.json or .cursor/mcp.json.

{
  "mcpServers": {
    "montycat-mcp": {
      "command": "uvx",
      "args": [
        "montycat-mcp"
      ],
      "env": {
        "MONTYCAT_URI": "...",
        "MONTYCAT_TLS": "...",
        "MONTYCAT_TLS_CERTIFICATE_PATH": "...",
        "MONTYCAT_TLS_VERIFY": "...",
        "MONTYCAT_TLS_CERTIFICATE_FINGERPRINT": "..."
      }
    }
  }
}

Fill in the environment variables with your own credentials.

• Runtime: Python with uv (runs with uvx) or Docker.
• MCP client: Claude Code, Codex, Antigravity, Claude Desktop, Cursor or any other client that speaks MCP over stdio.
• Environment variables: MONTYCAT_URI, MONTYCAT_TLS, MONTYCAT_TLS_CERTIFICATE_PATH, MONTYCAT_TLS_VERIFY, MONTYCAT_TLS_CERTIFICATE_FINGERPRINT