Computer Use

v1.0.0Browser Automationstable

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

mcp-servermodel-context-protocol
Share:
265
Stars
0
Downloads
0
Weekly
0/5

What is Computer Use?

Computer Use is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 💻 give ai models complete control of your computer (probably a bad idea)

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

This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 💻 Give AI models complete control of your computer (probably

Use Cases

Give AI complete control of your computer via MCP.
Automate desktop and system tasks with natural language.
Enable autonomous computer control for AI agents.
spencerkinney

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx computer-use

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Computer Use

Computer Use MCP gives AI models direct control of a computer through a structured set of mouse, keyboard, screenshot, and shell tools powered by the Orgo cloud service and Claude AI. It exposes primitives like click, type, scroll, execute_bash, and get_screenshot, as well as a high-level prompt tool that delegates autonomous multi-step tasks to Claude. Developers use it to build AI agents that can operate desktop applications, automate repetitive GUI workflows, and interact with software that has no API.

Prerequisites

  • Python 3.10+ with pip
  • An Orgo account and ORGO_API_KEY (https://orgo.ai)
  • An Anthropic API key (ANTHROPIC_API_KEY) for the Claude AI integration
  • An MCP client such as Claude Desktop
1

Create a virtual environment and install dependencies

Set up an isolated Python environment and install the required packages: fastmcp, pydantic, and the orgo client library.

python3 -m venv mcp-env
source mcp-env/bin/activate
pip install fastmcp pydantic orgo
2

Clone the repository

Download the Computer Use MCP server source code from GitHub.

git clone https://github.com/spencerkinney/computer-use-mcp.git
cd computer-use-mcp
3

Set required environment variables

Export your Orgo and Anthropic API keys. These are required for the server to authenticate with both services.

export ORGO_API_KEY=your_orgo_api_key_here
export ANTHROPIC_API_KEY=your_anthropic_api_key_here
4

Start the MCP server

Run the FastMCP server script. It will start listening for tool calls from your MCP client.

python computer_mcp_server.py
5

Add the server to your MCP client config

Configure Claude Desktop or another MCP client to launch the server automatically, passing the API keys as environment variables.

{
  "mcpServers": {
    "computer-use": {
      "command": "python",
      "args": ["/absolute/path/to/computer-use-mcp/computer_mcp_server.py"],
      "env": {
        "ORGO_API_KEY": "your_orgo_api_key_here",
        "ANTHROPIC_API_KEY": "your_anthropic_api_key_here"
      }
    }
  }
}

Computer Use Examples

Client configuration

Claude Desktop config that launches the Computer Use MCP server with both required API keys.

{
  "mcpServers": {
    "computer-use": {
      "command": "python",
      "args": ["/Users/you/computer-use-mcp/computer_mcp_server.py"],
      "env": {
        "ORGO_API_KEY": "orgo_live_xxxxxxxxxxxx",
        "ANTHROPIC_API_KEY": "sk-ant-xxxxxxxxxxxx"
      }
    }
  }
}

Prompts to try

Example prompts that exercise the computer control tools.

- "Take a screenshot of my screen and tell me what applications are open."
- "Open Firefox and navigate to news.ycombinator.com."
- "Click the search bar, type 'MCP server tutorial', and press Enter."
- "Run the command 'df -h' in a terminal and show me the output."
- "Scroll down the current page and take another screenshot."

Troubleshooting Computer Use

Server fails to start with 'orgo module not found'

Make sure you activated the virtual environment before running pip install (source mcp-env/bin/activate). Verify the install succeeded with: pip show orgo.

Tool calls fail with authentication errors

Double-check that ORGO_API_KEY and ANTHROPIC_API_KEY are set correctly. API keys should be exported before launching the server, or placed in the env block of your MCP client config.

Screenshots return blank or black images

The Orgo service controls a remote or virtual desktop. Ensure your Orgo session is active and the computer session is initialized using the initialize_computer tool before calling get_screenshot.

Frequently Asked Questions about Computer Use

What is Computer Use?

Computer Use is a Model Context Protocol (MCP) server that 💻 give ai models complete control of your computer (probably a bad idea) It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Computer Use?

Follow the installation instructions on the Computer Use GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Computer Use?

Computer Use works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Computer Use free to use?

Yes, Computer Use is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Browser Automation MCP Servers

Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "computer-use": { "command": "npx", "args": ["-y", "computer-use"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Computer Use?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides