Log inSubmit server
Computer Use logo

Computer Use

Controls a local desktop through screenshots, mouse actions, and keyboard automation for supervised AI interaction.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Computer Use

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "computer-use": {
      "command": "npx",
      "args": [
        "-y",
        "computer-use-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y computer-use-mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 3d ago.

Overview

Computer Use MCP server gives an AI model access to a local computer through screenshots, mouse control, and keyboard automation. It follows a computer-use interface similar to Anthropic’s approach and communicates with the desktop through nut.js. Install it through the provided setup flow, which generates configuration for supported MCP clients. Use it for supervised desktop tasks, preferably with a small display resolution and a sandboxed user account.

Use cases

  • Automate desktop applications through visible interfaces
  • Change local computer settings with model-guided actions
  • Navigate websites using screenshots and keyboard input
  • Test computer-use behavior in a sandboxed account

Key features

  • Capture desktop screenshots
  • Automate mouse actions
  • Automate keyboard input
  • Prefer keyboard shortcuts for interaction
  • Connect through nut.js
  • Run locally through an MCP client

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

7/7 checks healthy over the last 31d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 10d ago via OSV.dev · computer-use-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars386Stargazers on the source repository.
npm downloads2.8kPackage downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Computer Use works

What Computer Use MCP server does

Computer Use exposes a local desktop to an AI model through an MCP interface. The model can inspect the screen with screenshots and interact with visible applications using mouse and keyboard automation. The project is designed to resemble Anthropic’s computer-use tool while being available as a locally installed MCP server.

This makes it suitable for tasks that require interacting with graphical applications rather than calling a structured API. Examples include changing desktop settings, navigating an application, or operating websites through visible controls. The model receives the current screen state and can then choose interaction steps based on what it sees.

The Computer Use MCP server grants the model broad control over the connected computer. That makes supervision important: the README warns that models can make mistakes and may be vulnerable to prompt injection. A separate sandboxed user account is worth considering for testing.

How it works

The server implements a computer-use-style tool based closely on Anthropic’s documented approach, with additional guidance favoring keyboard shortcuts. It connects to the host computer through nut.js, which handles the underlying desktop interaction. The available interaction model is therefore based on screenshots, pointer actions, and keyboard input rather than application-specific APIs.

Results depend on the model’s ability to interpret screen content and choose reliable actions. The project recommends using a model that performs well at computer-use tasks. A 720p display resolution is suggested because smaller, common resolutions can make visual interaction easier. On macOS, the related displayoverride-mac project can be used to change the display resolution; if that is not possible, zooming the active window may help.

For browser tasks, the README recommends the Rango browser extension. Its keyboard-navigation hints can be more dependable than asking the model to click exact screen coordinates, and its font-size setting can be increased to make those hints easier to see.

Setup and configuration

The README directs users to the install-mcp setup page. That flow generates the MCP client configuration needed to run the package with npx, using the computer-use-mcp package. It lists Claude Code, Claude Desktop, Cursor, Cline, and VS Code among the clients for which configuration can be generated.

The project describes the default setup as requiring no additional configuration. For development, contributors need Git and Node.js, then install dependencies with npm install, run tests with npm run test, and build with npm run build. These development steps are separate from the normal client installation path.

Limitations and notes

Treat the Computer Use MCP server as a high-risk automation tool. Because the model can control the computer, an incorrect action or a prompt injection could affect files, settings, applications, or other data available to the account. Closely supervise sessions and avoid giving it unrestricted access to an important workstation.

It also does not claim that every model or display configuration will work equally well. Resolution, browser navigation, and model choice can all affect reliability.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Computer Use

Computer Use is an MCP server that connects an AI model to your local computer through screenshots, mouse control, and keyboard automation. It exposes a computer-use-style interface based on Anthropic’s approach, uses nut.js underneath, and is intended for supervised desktop interaction rather than unattended access.

Use the linked install-mcp setup page to generate configuration for your MCP client. The generated setup runs the computer-use-mcp package with npx.

The install-mcp page can generate the client configuration, after which Cursor can connect to the local server.

Use a model suited to computer-use tasks, try a small resolution such as 720p, and consider the Rango browser extension for keyboard navigation. Zooming active windows can also help when changing resolution is not possible.

Related MCP servers

All in OS Automation All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewComputer Use AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/computer-use?style=directory)](https://allmcps.com/mcp/computer-use)
HTML Embed
<a href="https://allmcps.com/mcp/computer-use"><img src="https://allmcps.com/api/badge/computer-use?style=directory" alt="Computer Use on AllMCPs" /></a>