What is Windows Mcp Server

Windows MCP is an open-source project that allows seamless integration between AI agents and the Windows operating system. It serves as an MCP server that connects LLMs (Language Learning Models) with Windows, enabling various tasks such as file management, application control, and user interface automation.

Use cases

Use cases for Windows MCP include automating file navigation, controlling applications, simulating user interactions, conducting QA testing, and integrating AI agents for various operational tasks within the Windows environment.

How to use

To use Windows MCP, first clone the repository and install the necessary dependencies. Then, configure the MCP server by modifying a JSON file with specific paths for your system. Finally, restart the client application (like Claude Desktop) to enable the integration and access the automation tools provided by Windows MCP.

Key features

Key features of Windows MCP include native Windows UI interaction, support for any LLM without reliance on computer vision, a rich set of UI automation tools, lightweight open-source architecture, and customizable options for tailored automation solutions.

Where to use

Windows MCP is specifically designed for use on Windows operating systems, including Windows 10 and Windows 11. It is ideal for environments where AI integration with desktop applications is required, such as in quality assurance, desktop automation tasks, and enhancing productivity through automated interactions.

🪟 Windows-MCP

Windows MCP is a lightweight, open-source project that enables seamless integration between AI agents and the Windows operating system. Acting as an MCP server bridges the gap between LLMs and the Windows operating system, allowing agents to perform tasks such as file navigation, application control, UI interaction, QA testing, and more.

https://github.com/user-attachments/assets/d0e7ed1d-6189-4de6-838a-5ef8e1cad54e

✨ Key Features

• Seamless Windows Integration
  Interacts natively with Windows UI elements, opens apps, controls windows, simulates user input, and more.

• Use Any LLM (Vision Optional)
  Unlike many automation tools, Windows MCP doesn’t rely on any traditional computer vision techniques or specific fine-tuned models; it works with any LLMs, reducing complexity and setup time.

• Rich Toolset for UI Automation
  Includes tools for basic keyboard, mouse operation and capturing window/UI state.

• Lightweight & Open-Source
  Minimal dependencies and easy setup with full source code available under MIT license.

• Customizable & Extendable
  Easily adapt or extend tools to suit your unique automation or AI integration needs.

• Real-Time Interaction
  Typical latency between actions (e.g., from one mouse click to the next) ranges from 4 to 8 secs, and may slightly vary based on the number of active applications and system load.

Supported Operating Systems

• Windows 10
• Windows 11

Installation

Prerequisites

• Python 3.12+
• Anthropic Claude Desktop app or other MCP Clients
• UV (Python package manager), install with pip install uv

🏁 Getting Started

1. Clone the repository.

git clone https://github.com/CursorTouch/Windows-MCP.git
cd Windows-MCP

2. Install dependencies:

uv sync

3. Connect to the MCP server

Copy the below JSON with the appropriate {{PATH}} values:

{
  "mcpServers": {
    "windows-mcp": {
      "command": "{{PATH_TO_UV}}",
      "args": [
        "--directory",
        "{{PATH_TO_SRC}}/Windows-MCP",
        "run",
        "main.py"
      ]
    }
  }
}

For Claude, save this as claude_desktop_config.json in your Claude Desktop configuration directory at:

%APPDATA%/Claude/claude_desktop_config.json

4. Restart Claude Desktop

Open Claude Desktop, and you should now see Windows-MCP as an available integration.

For additional Claude Desktop integration troubleshooting, see the MCP documentation. The documentation includes helpful tips for checking logs and resolving common issues.

🛠️MCP Tools

Claude can access the following tools to interact with Windows:

• Click-Tool: Click on the screen at the given coordinates.
• Type-Tool: Type text on an element (optionally clears existing text).
• Clipboard-Tool: Copy or paste using the system clipboard.
• Scroll-Tool: Scroll vertically or horizontally on the window or specific regions.
• Drag-Tool: Drag from one point to another.
• Move-Tool: Move mouse pointer.
• Shortcut-Tool: Press keyboard shortcuts (Ctrl+c, Alt+Tab, etc).
• Key-Tool: Press a single key.
• Wait-Tool: Pause for a defined duration.
• State-Tool: Combined snapshot of active apps and interactive, textual and scrollable elements along with screenshot of the desktop.
• Screenshot-Tool: Capture a screenshot of the desktop.
• Launch-Tool: To launch an application from the start menu.
• Shell-Tool: To execute PowerShell commands.
• Scrape-Tool: To scrape the entire webpage for information.

⚠️Caution

This MCP interacts directly with your Windows operating system to perform actions. Use with caution and avoid deploying it in environments where such risks cannot be tolerated.

🪪License

This project is licensed under the MIT License - see the LICENSE file for details.

🤝Contributing

Contributions are welcome! Please see CONTRIBUTING for setup instructions and development guidelines.

Made with ❤️ by Jeomon George

Citation

@software{
  author       = {George, Jeomon},
  title        = {Windows-MCP: Lightweight open-source project for integrating LLM agents with Windows},
  year         = {2024},
  publisher    = {GitHub},
  url={https://github.com/CursorTouch/Windows-MCP}
}