Computer Use
💻 Give AI models complete control of your computer (probably a bad idea)
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
Maintainer
Works with
Installation
Manual Installation
npx computer-useConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
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
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 orgoClone 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-mcpSet 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_hereStart the MCP server
Run the FastMCP server script. It will start listening for tool calls from your MCP client.
python computer_mcp_server.pyAdd 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.
Computer Use Alternatives — Similar Browser Automation Servers
Looking for alternatives to Computer Use? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.
Chrome DevTools MCP
★ 40.6kAI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo
UI TARS Desktop
★ 34.9k📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Playwright
★ 32.8kA production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa
Page Agent
★ 18.0kJavaScript in-page GUI agent. Control web interfaces with natural language.
Chrome
★ 11.7kAn extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,
LAMDA
★ 7.8kThe most powerful Android RPA agent framework, next generation mobile automation.
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.
Set Up Computer Use in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
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.