Windows Desktop Automation MCP server

This MCP server provides Windows desktop automation capabilities through AutoIt functions, allowing language models to control mouse, keyboard, windows, and other system operations via the Model Context Protocol.

Installation

To set up the MCP Windows Desktop Automation server:

# 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

Starting the Server

You can run the server with different transport options:

# Start with stdio transport (default)
npm start

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

# Enable verbose logging
npm start -- --verbose

Command Line Options

The server supports these configuration options:

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

Available Tools

The MCP server exposes all AutoIt functions as tools, organized into the following categories:

Mouse Operations

• Move the cursor
• Perform clicks (left, right, middle)
• Drag and drop operations

Keyboard Operations

• Send keystrokes to applications
• Manipulate the clipboard
• Type text

Window Management

• Find windows by title or other attributes
• Activate, minimize, or close windows
• Resize and reposition windows

Control Manipulation

• Interact with UI elements like buttons and text fields
• Select items from menus and lists
• Get and set control values

Process Management

• Start and stop applications
• Monitor running processes

System Operations

• Control system power states (shutdown, sleep)
• Run system commands

Working with Resources

The server provides access to these resources:

File Access

• Read files from the system
• List directory contents

Screenshots

• Capture the entire screen
• Take screenshots of specific windows
• Use images for visual automation tasks

Prompt Templates

The server includes templates for common automation scenarios:

• Window interaction workflows
• Form filling operations
• Repetitive task automation
• Condition monitoring and waiting

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.