MCP Windows Desktop Automation

🚀 Windows Desktop Automation MCP Server

A Windows desktop automation Model Context Protocol (MCP) server implemented using AutoIt.

🚀 Quick Start

This project offers a TypeScript MCP server that encapsulates the node-autoit-koffi package. It enables LLM applications to automate Windows desktop tasks via the MCP protocol.

The server exposes:

• Tools: All AutoIt functions as MCP tools.
• Resources: File access and screenshot capabilities.
• Prompts: Templates for common automation tasks.

✨ Features

• Fully encapsulates all AutoIt functions as MCP tools.
• Supports stdio and WebSocket transport protocols.
• Provides file access resources for reading files and directories.
• Offers screenshot resources for capturing the screen or specific windows.
• Includes prompt templates for common automation tasks.
• Strictly uses TypeScript types.

📦 Installation

# Clone the repository
git clone https://github.com/yourusername/mcp-windows-desktop-automation.git
cd mcp-windows-desktop-automation

# Install dependencies
npm install

# Build the project
npm run build

💻 Usage Examples

Starting the Server

# Start via stdio transport (default)
npm start

# Start via WebSocket transport
npm start -- --transport=websocket --port=3000

# Enable verbose logging
npm start -- --verbose

Command-line Options

• --transport=stdio|websocket: Specify the transport protocol (default: stdio).
• --port=<number>: Specify the port for WebSocket transport (default: 3000).
• --verbose: Enable verbose logging.

Tools

The server provides the following tools for:

• Mouse operations: Moving, clicking, dragging, etc.
• Keyboard operations: Sending keystrokes, clipboard operations, etc.
• Window management: Finding, activating, closing, resizing windows, etc.
• Control operations: Interacting with UI controls such as buttons and text boxes.
• Process management: Starting, stopping, and monitoring processes.
• System operations: Shutting down, putting the system to sleep, etc.

Resources

The server provides the following resources for:

• File access: Reading files and listing directories.
• Screenshots: Capturing the screen or specific windows.

Prompts

The server provides the following prompt templates for:

• Window interaction: Finding and interacting with windows.
• Form filling: Automating form-filling tasks.
• Automation tasks: Creating scripts for repetitive tasks.
• Monitoring: Waiting for specific conditions.

Development

# Run in development mode
npm run dev

# Check code style
npm run lint

# Run tests
npm run test

📄 License

MIT