Sandbox
@domdomegg/computer-use-mcp

MCP server for computer control from your agent

This repository provides a local MCP server that gives Claude or another MCP client control of your computer. It follows Anthropic-style computer use patterns and uses `nut.js` under the hood for desktop actions.

364 stars41 forksTypeScriptUpdated 7d ago
Who it's for

Builders who want an MCP client to click, type, and navigate their desktop.

What it delivers

You can let an agent operate your computer directly instead of switching between chat and manual actions.

What it does

Desktop control via MCP

Exposes computer-use actions through a Model Context Protocol server.

Local computer automation

Uses `nut.js` to drive mouse and keyboard actions on your machine.

Client setup support

Provides install guidance for MCP clients such as Claude Code, Claude Desktop, and Cursor through install-mcp.

Packaging and release scripts

Includes `build-mcpb.sh` and release steps for building and publishing the package.

README

computer-use-mcp

💻 A Model Context Protocol server for Claude to control your computer. This is very similar to computer use, but easy to set up and use locally.

Here's Claude Haiku 4.5 changing my desktop background (4x speed):

https://github.com/user-attachments/assets/cd0bc190-52c4-49db-b3bc-4b8a74544789

[!WARNING] At time of writing, models make frequent mistakes and are vulnerable to prompt injections. As this MCP server gives the model complete control of your computer, this could do a lot of damage. You should therefore treat this like giving a hyperactive toddler access to your computer - you probably want to supervise it closely, and consider only doing this in a sandboxed user account.

Installation

Follow the instructions on install-mcp, which generates the right config for your MCP client (Claude Code, Claude Desktop, Cursor, Cline, VS Code, and more).

Tips

This should just work out of the box.

However, to get best results:

  • Use a model good at computer use - I recommend the latest Claude models.
  • Use a small, common resolution - 720p works particularly well. On macOS, you can use displayoverride-mac to do this. If you can't use a different resolution, try zooming in to active windows.
  • Install and enable the Rango browser extension. This enables keyboard navigation for websites, which is far more reliable than Claude trying to click coordinates. You can bump up the font size setting in Rango to make the hints more visible.

How it works

We implement a near identical computer use tool to Anthropic's official computer use guide, with some more nudging to prefer keyboard shortcuts.

This talks to your computer using nut.js

Contributing

Pull requests are welcomed on GitHub! To get started:

  1. Install Git and Node.js
  2. Clone the repository
  3. Install dependencies with npm install
  4. Run npm run test to run tests
  5. Build with npm run build

Releases

Versions follow the semantic versioning spec.

To release:

  1. Use npm version <major | minor | patch> to bump the version
  2. Run git push --follow-tags to push with tags
  3. Wait for GitHub Actions to publish to the NPM registry.

Files in the repo

Repository payload14 top-level entries
  • .github
  • src
  • .gitignore
  • build-mcpb.sh
  • eslint.config.mjs
  • icon.png
  • LICENSE
  • manifest.json
  • package-lock.json
  • package.json
  • README.md
  • server.json
  • tsconfig.build.json
  • tsconfig.json

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k
t8y2/dbxConnectors

20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。

19k