# Handsy AI (MCP server)

> Handsy AI is an MCP server that lets AI agents see and operate a real iPhone via an ESP32-S3 USB HID + AirPlay. It has 5,012 GitHub stars, is released under the MIT license and runs locally with npx -y esp32agent.

An AI agent uses a real iPhone like a person. It even made a phone call on its own. No jailbreak, no developer account, open source.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/onehumanbeing/esp32-iphone-agent |
| GitHub stars | 5,012 |
| License | MIT |
| Language | Swift |
| Transport | stdio |
| Packages | npm: esp32agent |
| Remote URL | none |
| Needs API key | no |
| Official | no |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | Other |
| Latest release | cli-v0.1.4 (Nov 8, 2026) |
| Last commit | Nov 16, 2026 |
| MCP registry name | io.github.onehumanbeing/esp32agent |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "handsy-ai": {
      "command": "npx",
      "args": [
        "-y",
        "esp32agent"
      ]
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --transport stdio handsy-ai -- npx -y esp32agent
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "handsy-ai": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "esp32agent"
      ]
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "handsy-ai": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "esp32agent"
      ]
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Similar MCP servers

- [Peekaboo](https://appsgit.com/mcp-servers/peekaboo): Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI… (5,490 stars, MIT)
- [Flint Chart](https://appsgit.com/mcp-servers/flint-chart): 🪄 Flint is a visualization language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs. (4,580 stars, MIT, official)
- [Remove AI Watermarks](https://appsgit.com/mcp-servers/remove-ai-watermarks): Identify and clean AI watermarks and provenance in your own images, video, and text. (6,407 stars, Apache-2.0)
- [MCP Server Chart](https://appsgit.com/mcp-servers/mcp-server-chart): A Model Context Protocol server for generating charts using AntV. (4,418 stars, MIT, needs API key)
- [Ha MCP](https://appsgit.com/mcp-servers/ha-mcp): Configure and automate Home Assistant with Claude, ChatGPT, and other AI assistants. (7,896 stars, MIT)
- [Microsoft Fabric MCP Server](https://appsgit.com/mcp-servers/microsoft-fabric-mcp-server): MCP tools for interacting with Microsoft Fabric. (3,861 stars, MIT, official)

---

Canonical page: https://appsgit.com/mcp-servers/handsy-ai
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed daily.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.
