computer-use-mcp

computer-use-mcp

0

The Computer Use MCP Server allows users to control virtual computers through the Model Context Protocol, providing tools for Computer Use Agents. It is built using FastMCP and Orgo, enabling cloud desktop environments.

Computer Use MCP Server 🖥️

Control virtual computers through the Model Context Protocol (MCP). Built with FastMCP and Orgo.

Spin up cloud desktop environments for Computer Use Agents (CUA).

Quick Start

1. Install Dependencies

# Create virtual environment
python3 -m venv mcp-env
source mcp-env/bin/activate

# Install packages
pip install fastmcp pydantic orgo

2. Get API Keys

3. Run Server

# Set environment variables
export ORGO_API_KEY="your_orgo_key"
export ANTHROPIC_API_KEY="your_anthropic_key"

# Start server
python computer_mcp_server.py

Server runs on http://127.0.0.1:9000

Test Client

import asyncio
from fastmcp import Client

async def demo():
    async with Client("http://127.0.0.1:9000/mcp") as client:
        # Initialize computer
        result = await client.call_tool("initialize_computer", {
            "api_key": "your_orgo_key"
        })
        print(f"Computer ready: {result[0].text}")
        
        # Take screenshot
        screenshot = await client.call_tool("get_screenshot")
        print("Screenshot taken!")
        
        # Click and type
        await client.call_tool("left_click", {"x": 100, "y": 200})
        await client.call_tool("type_text", {"text": "Hello World"})
        await client.call_tool("press_key", {"key": "Enter"})

if __name__ == "__main__":
    asyncio.run(demo())

Available Tools

ToolDescription
initialize_computerStart virtual computer
get_screenshotTake screen capture
left_click, right_click, double_clickMouse actions
scrollScroll up/down
type_text, press_keyKeyboard input
waitWait for specified seconds
execute_bashRun terminal commands
restart_computer, shutdown_computerComputer lifecycle
get_status, list_sessionsStatus and session management
promptClaude AI Computer Use

Claude AI Computer Use Example

# Let Claude control the computer
await client.call_tool("prompt", {
    "instruction": "Open Firefox and go to google.com"
})

Requirements

  • Python 3.8+
  • Orgo API key
  • Anthropic API key (for Claude CUA)