# memo MCP server

> Keep persistent, searchable memory for coding agents, stored as Markdown and run entirely on your own machine.

- Listing: https://mcp.tc/i/memo
- Connect: this is a local (stdio) server; install it on your machine (see Install). The listing link is a page, not an MCP endpoint.
- Type: local (stdio)
- Auth: no API key needed
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: jagoff
- Homepage: <https://memo-web-sigma.vercel.app>
- Repository: <https://github.com/jagoff/memo>
- Package: pypi `mlx-memo`

## About

memo gives MCP clients such as Claude Code, Codex, Cursor, Cline, Devin and OpenCode a persistent memory. Memories are plain Markdown files, indexed in SQLite with hybrid search that combines vector embeddings (MLX on Apple Silicon, sentence-transformers on CPU) and BM25. It also offers a time-machine for past states, contradiction scanning and a nightly maintenance run.

It runs locally over stdio from the mlx-memo PyPI package, with no cloud service and no API keys. The default MCP profile exposes 43 tools, with larger profiles available. It needs Python 3.13 or newer, and the first install downloads about 8 GB of models. macOS on Apple Silicon is fully supported; Linux and Docker use the CPU backend.

## What it can do

- Save decisions and notes as Markdown memories
- Search memories by meaning with hybrid vector and BM25 retrieval
- Query knowledge as it was on a past date
- Scan for and resolve contradicting facts
- Resume sessions across different agents
- Sync memory between machines through your own git remote

## Example prompts

- "Save a memory that we use Postgres, not Mongo"
- "Search my memory for what database we picked"
- "What was our deploy strategy on 2026-02-01?"
- "Scan my memories for contradicting decisions"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport stdio memo -- uvx mlx-memo
```

2. Start Claude Code and type `/mcp`. **memo** should show as connected.

Add `--scope user` to make it available in every project.

### Claude Desktop

1. Open **Settings → Developer → Edit Config**. It opens `claude_desktop_config.json`. Add:

`claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "memo": {
      "command": "uvx",
      "args": [
        "mlx-memo"
      ]
    }
  }
}
```

2. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in `~/Library/Application Support/Claude/` on macOS and `%APPDATA%\Claude\` on Windows.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=memo&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJtbHgtbWVtbyJdfQ%3D%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "memo": {
      "command": "uvx",
      "args": [
        "mlx-memo"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=memo&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22mlx-memo%22%5D%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"memo","type":"stdio","command":"uvx","args":["mlx-memo"]}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "memo": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mlx-memo"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "memo": {
      "command": "uvx",
      "args": [
        "mlx-memo"
      ]
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

### Codex

```bash
codex mcp add memo -- uvx mlx-memo
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.memo]
command = "uvx"
args = ["mlx-memo"]
```

Needs uv (Python) on your computer.

### Gemini CLI

```bash
gemini mcp add memo uvx mlx-memo
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients that start local servers accept this shape:

```json
{
  "mcpServers": {
    "memo": {
      "command": "uvx",
      "args": [
        "mlx-memo"
      ]
    }
  }
}
```

Zed puts servers under `context_servers` in its settings, with the same `command`, `args` and `env` fields.

Needs uv (Python) on your computer.

## Details

- Server version: 4.16.0
- Last checked: 2026-10-04
- Listed: 2026-10-04
- Updated: 2026-10-04

---
Source: https://mcp.tc/i/memo (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report