# Persome MCP server

> Serve a local, inspectable personal memory and model built from your macOS app activity to trusted MCP agents.

- Listing: https://mcp.tc/i/persome
- 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: Intuition-Lab
- Homepage: <https://intuition-lab.github.io/personal-model/>
- Docs: <https://github.com/Intuition-Lab/personal-model/tree/main/docs>
- Repository: <https://github.com/Intuition-Lab/personal-model>
- Package: pypi `personal-model`

## About

Persome is a local-first personal model runtime for macOS. It collects focused Accessibility context across apps, with optional on-device OCR, turns it into sourced facts, relations and patterns, and serves that memory and model to MCP clients such as Claude Code, Codex and Cursor. It also provides receipts, time travel, correction, export and deletion.

It runs locally and is installed from PyPI as personal-model (CLI: persome), using uv. The MCP server listens on loopback only and requires an owner-local bearer token. Installation needs macOS 13 or newer, and onboarding requests Accessibility permission. An LLM provider API key is configured during setup for modeling stages. A synthetic sample demo runs without a key or permissions.

## What it can do

- Capture focused macOS Accessibility context across apps
- Optional on-device OCR for apps with poor Accessibility data
- Build sourced facts, relations and patterns into a personal model
- Serve memory and model tools to MCP agents over local HTTP
- Inspect, correct, export and delete stored data
- Run a synthetic sample demo with no personal data

## Example prompts

- "Search my personal memory for what I was working on in Xcode yesterday."
- "Show the current Root of my personal model."
- "What do I usually do when preparing a weekly report?"
- "Correct the fact about my preferred editor in my personal model."

## Install

### Claude Code

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

```bash
claude mcp add --transport stdio persome -- uvx personal-model
```

2. Start Claude Code and type `/mcp`. **persome** 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": {
    "persome": {
      "command": "uvx",
      "args": [
        "personal-model"
      ]
    }
  }
}
```

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=persome&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJwZXJzb25hbC1tb2RlbCJdfQ%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": {
    "persome": {
      "command": "uvx",
      "args": [
        "personal-model"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### VS Code

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

Or from a terminal:

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

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

`.vscode/mcp.json`:

```json
{
  "servers": {
    "persome": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "personal-model"
      ]
    }
  }
}
```

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": {
    "persome": {
      "command": "uvx",
      "args": [
        "personal-model"
      ]
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

### Codex

```bash
codex mcp add persome -- uvx personal-model
```

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

`config.toml`:

```toml
[mcp_servers.persome]
command = "uvx"
args = ["personal-model"]
```

Needs uv (Python) on your computer.

### Gemini CLI

```bash
gemini mcp add persome uvx personal-model
```

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": {
    "persome": {
      "command": "uvx",
      "args": [
        "personal-model"
      ]
    }
  }
}
```

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

Needs uv (Python) on your computer.

## Recent changes

- 2026-10-08 04:20 UTC: Tracking started: version 0.3.2. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/persome#history (Atom feed: https://mcp.tc/i/persome/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 0.3.2
- Last checked: 2026-10-08
- Listed: 2026-10-08
- Updated: 2026-10-08

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