Skip to content
Back to search

computer-use-mcp

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

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/domdomegg/computer-use-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/domdomegg/computer-use-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/domdomegg--computer-use-mcp/badge.svg)](/listings/domdomegg--computer-use-mcp)

HTML

<a href="/listings/domdomegg--computer-use-mcp"><img src="/api/listings/domdomegg--computer-use-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 49 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # computer-use-mcp
  2. 💻 A Model Context Protocol server for Claude to control your computer. This is very similar to [computer use](https://docs.anthropic.com/en/docs/build-with-claude/computer-use), but easy to set up and use locally.
  3. Here's Claude Haiku 4.5 changing my desktop background (4x speed):
  4. https://github.com/user-attachments/assets/cd0bc190-52c4-49db-b3bc-4b8a74544789
  5. > [!WARNING]
  6. > 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.
  7. ## Installation
  8. Follow the instructions on [install-mcp](https://adamjones.me/install-mcp/?config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsImNvbXB1dGVyLXVzZS1tY3AiXSwibmFtZSI6ImNvbXB1dGVyLXVzZSJ9), which generates the right config for your MCP client (Claude Code, Claude Desktop, Cursor, Cline, VS Code, and more).
  9. ## Tips
  10. This should just work out of the box.
  11. However, to get best results:
  12. - Use a model good at computer use - I recommend [the latest Claude models](https://platform.claude.com/docs/en/about-claude/models/overview).
  13. - Use a small, common resolution - 720p works particularly well. On macOS, you can use [displayoverride-mac](https://github.com/domdomegg/displayoverride-mac) to do this. If you can't use a different resolution, try zooming in to active windows.
  14. - Install and enable the [Rango browser extension](https://chromewebstore.google.com/detail/rango/lnemjdnjjofijemhdogofbpcedhgcpmb). 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.
  15. ## How it works
  16. We implement a near identical computer use tool to [Anthropic's official computer use guide](https://docs.anthropic.com/en/docs/build-with-claude/computer-use), with some more nudging to prefer keyboard shortcuts.
  17. This talks to your computer using [nut.js](https://github.com/nut-tree/nut.js)
  18. ## Contributing
  19. Pull requests are welcomed on GitHub! To get started:
  20. 1. Install Git and Node.js
  21. 2. Clone the repository
  22. 3. Install dependencies with `npm install`
  23. 4. Run `npm run test` to run tests
  24. 5. Build with `npm run build`
  25. ## Releases
  26. Versions follow the [semantic versioning spec](https://semver.org/).
  27. To release:
  28. 1. Use `npm version <major | minor | patch>` to bump the version
  29. 2. Run `git push --follow-tags` to push with tags
  30. 3. Wait for GitHub Actions to publish to the NPM registry.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.