Control Remote macOS Desktops with AI

Remote MacOS Use is an open-source MCP server that lets an AI fully control remote macOS systems through screen sharing, positioned as a direct alternative to OpenAI Operator with complete desktop capabilities. It works by connecting to the target Mac's built-in Screen Sharing feature - no background app or agent needs to be installed on the target machine - and it uses your existing Claude Pro plan's screen processing rather than a separate paid API. It supports WebRTC via LiveKit for low-latency, real-time screen demonstration with automatic quality adaptation to network conditions, and it works with any MCP client and any LLM provider (OpenAI, Anthropic, or others).

Use this when an AI agent needs to operate a remote Mac's full desktop - opening applications, navigating the UI, filling forms, or automating multi-step workflows - as if it were a human sitting at that machine. Example use cases include researching and posting to Twitter, using CapCut to create a highlight video, or running an automated recruiter workflow that collects candidate info and sends screening sessions via Mail. It requires Screen Sharing enabled on the target macOS machine and only supports Apple Authentication (protocol 30); it is not a solution for controlling non-macOS remote systems, and real-time WebRTC performance requires configuring a LiveKit server.

• remote_macos_get_screen - connects to the remote Mac and captures a screenshot of its desktop
• remote_macos_send_keys - sends keyboard input to the remote machine
• remote_macos_mouse_move - moves the mouse cursor to specified coordinates, with automatic coordinate scaling
• remote_macos_mouse_click / remote_macos_mouse_double_click - clicks or double-clicks at specified coordinates
• remote_macos_mouse_scroll - scrolls at specified coordinates
• remote_macos_open_application - opens/activates an application and returns its PID for further interaction
• remote_macos_mouse_drag_n_drop - drags from a start point to an end point

Security note: the connection uses Diffie-Hellman key negotiation with a 512-bit prime for the Apple screen-sharing protocol.

Via Docker:

docker run -i -e MACOS_USERNAME=your_macos_username -e MACOS_PASSWORD=your_macos_password -e MACOS_HOST=your_macos_hostname_or_ip --rm buryhuang/mcp-remote-macos-use:latest

Claude Desktop configuration:

{
  "mcpServers": {
    "remote-macos-use": {
      "command": "docker",
      "args": ["run", "-i", "-e", "MACOS_USERNAME=your_macos_username", "-e", "MACOS_PASSWORD=your_macos_password", "-e", "MACOS_HOST=your_macos_hostname_or_ip", "--rm", "buryhuang/mcp-remote-macos-use:latest"]
    }
  }
}

Required environment variables: MACOS_USERNAME, MACOS_PASSWORD, MACOS_HOST.

Developers and teams automating macOS-specific workflows - social media management, video editing via desktop apps, recruiting pipelines, marketing engagement - who want an AI to drive the full desktop of a remote Mac without installing any agent software on it.