What is a memory MCP?

Magnemo — Tue, 13 Oct 2026 04:08:14 +0000

A memory MCP is a server that gives your agent a record of what it learned across sessions; Magnemo is one, kept as plain files you own.

Two things are called memory

The word covers two different jobs. One is a code index of your repo: a search over files, symbols and history so the agent can find things. The other is what your agent learned and decided: why you chose that schema, which fix failed, what the next session should do first. An index can be rebuilt from the code. Decisions cannot, once the context window closes and compaction guesses at what mattered. Magnemo is the second kind.

The four tools

retrieve reads canon, the notes a person has approved.
stage proposes a note. The agent can propose, nothing more.
bootpack returns what the next session reads first.
handoff closes a session with a note for the next one.

Paste and config

Install, then make a vault, which is a folder of markdown files:

pip install magnemo
magnemo init ./vault

Or run it with uvx magnemo-mcp. Then add this to your MCP client's config, with an absolute path:

{
  "mcpServers": {
    "magnemo": {
      "command": "magnemo-mcp",
      "env": { "MAGNEMO_VAULT": "/absolute/path/to/vault" }
    }
  }
}

Claude Code is the tested client; Claude Desktop, Cursor and other MCP clients take the same block and are untested here. A staged note is kept when magnemo yes is run on it. Promotion is not an MCP tool. Every entry records who wrote it, who approved it, and when. A newer note supersedes an older one, and the older one is archived with its words intact. Notes that look like secrets or injected instructions are tainted at the door and never served through the server.

DEV Community: Magnemo

What is a memory MCP?

Two things are called memory

The four tools

Paste and config

Related questions