Skip to main content

Connect Claude to Mnemosyne (MCP)

Your memory can be a tool your AI tools use. The @mnemosyne_os/mcp package (MIT) is a Model Context Protocol server that turns your local Mnemosyne OS install into a queryable memory layer for Claude Desktop, Claude Code, Cursor, Hermes Agent — any agent that speaks MCP.

Once connected, your agent can:

  • Query your code, decisions, architecture notes and git history with true semantic ranking;
  • Persist new decisions and insights, so future sessions recover them;
  • Resume a project exactly where you left off;
  • Filter by the nature of memories (ARCHITECTURE, SOURCE_CODE, GIT, BUGFIX…).

Everything stays on your machine. The MCP is a thin bridge — it stores nothing itself; all data lives in your Mnemosyne OS vaults, and the agent only sees the vaults you allow.

It runs on itself

The Neural Map video on this wiki is Mnemosyne remembering her own development — and this very wiki is written by an agent connected through this exact MCP.

Requirements

  1. Mnemosyne OS running — the app owns your vaults and exposes the local gateway the MCP talks to. The bridge works only while the app is open.
  2. Node.js ≥ 18.

Claude Desktop

Settings → Developer → Edit config (claude_desktop_config.json), add:

{
"mcpServers": {
"mnemosyne": {
"command": "npx",
"args": ["-y", "@mnemosyne_os/mcp"],
"env": {
"MNEMO_DEFAULT_VAULT": "DEV",
"MNEMO_VAULTS": "DEV,PERSONAL,SOCIAL"
}
}
}
}

Fully quit and relaunch Claude Desktop (from the tray icon, not just the window). The mnemosyne server appears under Settings → Developer → Local MCP Servers with the running badge.

Claude Code

Add .mcp.json at the root of your project with the same block, then reload the session:

{
"mcpServers": {
"mnemosyne": {
"command": "npx",
"args": ["-y", "@mnemosyne_os/mcp"],
"env": {
"MNEMO_DEFAULT_VAULT": "DEV",
"MNEMO_VAULTS": "DEV,PERSONAL,SOCIAL"
}
}
}
}

Cursor

Same block again, in .cursor/mcp.json.

Hermes Agent

Hermes ships with MCP support — no extra install. The recipe lives in the package README.

You stay the gate

MNEMO_VAULTS names the vaults the agent may see — nothing else is reachable, and Maximum-protection vaults keep their guarantees. Writes go through the same governed doors as everything else. Your claude.ai conversation never sees your code — only the chronicles you allow.