MemoCat — Shared AI Memory

local MCP server

Installation

Terminal

claude mcp add memocat-mcp -e MONTYCAT_URI=... -e MONTYCAT_TLS=... -- uvx memocat-mcp

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

Claude Desktop, Cursor & other clients

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

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

Fill in the environment variables with your own credentials.

Summary

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

Questions

MemoCat — Shared AI Memory is a local MCP server distributed as the pypi package memocat-mcp.

Run: claude mcp add memocat-mcp -e MONTYCAT_URI=... -e MONTYCAT_TLS=... -- uvx memocat-mcp

Run: codex mcp add memocat-mcp --env MONTYCAT_URI=... --env MONTYCAT_TLS=... -- uvx memocat-mcp

Similar MCP servers

NameStars

Montycat MCP - Shared Memory for AI Agentsio.github.MontyGovernance/montycat-mcp65
token-saviorio.github.Mibayy/token-savior1,157
YourMemoryio.github.sachitrafa/yourmemory270
neural-memoryio.github.nhadaututtheky/neural-memory240
DeepMemio.github.deepmemteam/deepmem114
Pensyveio.github.major7apps/pensyve87
Synap Memoryai.maximem/synap74
Total Agent Memoryio.github.vbcherepanov/total-agent-memory72