domdomegg/computer-use-mcp

💻 Give AI models complete control of your computer (probably a bad idea)

What it solves

It provides a simplified way to let AI models, specifically Claude, control a local computer. It removes the complexity of setting up official computer-use environments by offering a local Model Context Protocol (MCP) server implementation.

How it works

The project implements a set of computer-use tools based on Anthropic's official guidelines, using the nut.js library to interact with the operating system. It encourages the use of keyboard shortcuts over coordinate-based clicking for higher reliability.

Who it’s for

Users who want to give AI agents the ability to operate their desktop environment locally and those using MCP-compatible clients like Claude Desktop, Cursor, or Cline.

Highlights

  • Local MCP server implementation for easier setup.
  • Compatible with multiple AI clients including Claude Code and VS Code.
  • Optimized for keyboard navigation to improve reliability.
  • Supports desktop automation tasks such as changing system settings.

Related

  • Project
    wonderwhy-er/DesktopCommanderMCP

    An MCP server that enables AI assistants to search, edit files, and execute terminal commands on your local machine, with support for advanced file types and process management.

  • Project
    homeassistant-ai/ha-mcp

    An MCP server that enables AI assistants to interact with Home Assistant, allowing users to control devices and manage automations using natural language.

  • Project
    motherduckdb/mcp-server-motherduck

    A self‑hosted MCP server that wraps DuckDB (local, S3, or MotherDuck) so AI assistants can run SQL queries via the Model‑Chat‑Protocol. Supports stdio or HTTP, read/write control, Docker deployment, and integrates with Claude, Gemini, Cursor, etc.

  • Dispatch
    Anthropic Model Context Protocol (MCP) Release

    Anthropic has open-sourced the Model Context Protocol (MCP), a universal standard for connecting AI assistants to data sources like content repositories, business tools, and development environments to eliminate fragmented integrations.

  • Project
    MiniMax-AI/MiniMax-MCP

    An official Model Context Protocol (MCP) server that enables AI clients like Claude and Cursor to generate speech, clone voices, and create images and videos using MiniMax APIs.