Windows MCP
Featuredby
Enables AI agents to control the Windows operating system, performing file navigation, application launching, UI interaction, QA testing, and other automation tasks through a lightweight server.
Windows MCP Overview
What is Windows MCP about?
Windows MCP provides a bridge between large language models and the Windows OS, allowing AI agents to interact with desktop elements—clicking, typing, launching apps, capturing state, and executing PowerShell commands—without relying on computer‑vision models.
How to use Windows MCP?
- Prerequisites: Install Python 3.13+ and the UV package manager (
pip install uv). - Clone the repo:
git clone https://github.com/CursorTouch/Windows-MCP.git cd Windows-MCP - Run the server (using UV):
uv run main.py - Integrate with clients – the README supplies ready‑to‑use JSON/TOML snippets for Claude Desktop, Perplexity Desktop, Gemini CLI, Qwen Code, and Codex CLI. Replace
<path to the windows-mcp directory>with the absolute path to the cloned folder.
Key Features of Windows MCP
- Seamless Windows integration – native interaction with UI elements, window management, and system clipboard.
- LLM‑agnostic – works with any LLM (vision optional), avoiding model‑specific dependencies.
- Rich toolset – Click‑Tool, Type‑Tool, Clipboard‑Tool, Scroll‑Tool, Drag‑Tool, Move‑Tool, Shortcut‑Tool, Key‑Tool, Wait‑Tool, State‑Tool, Resize‑Tool, Launch‑Tool, Shell‑Tool, Scrape‑Tool.
- Lightweight & open‑source – minimal dependencies, MIT‑licensed.
- Customizable & extensible – easy to add or modify tools for specific workflows.
- Real‑time interaction – typical latency of 0.7‑2.5 seconds per action, depending on system load and LLM inference speed.
Use Cases of Windows MCP
- Automated UI testing and regression checks.
- AI‑driven personal assistants that schedule, browse files, and control applications.
- Remote desktop automation for support or managed services.
- Data entry and batch processing across legacy Windows applications.
- Screen scraping and information extraction from desktop apps.
FAQ from the Windows MCP
Q: Which Windows versions are supported? A: Windows 7, 8, 8.1, 10, and 11.
Q: Do I need a specific LLM or vision model? A: No. Any LLM that can generate text commands works; vision is optional.
Q: Can I run the server on non‑English Windows installations?
A: English is preferred. If using another language, disable Launch-Tool and Switch-Tool in the server configuration.
Q: Is the server safe to run on production machines? A: The server issues real OS actions, so it should be used with caution and not in environments where uncontrolled automation is risky.
Q: Why does typing sometimes fail in IDEs?
A: Type-Tool sends whole‑text input and is not optimized for incremental code editing. This limitation is being addressed.
Q: Can it be used for gaming? A: No. The server is not designed for high‑frequency game input.
Windows MCP's README
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.
mcp-name: io.github.CursorTouch/Windows-MCP
Updates
- Windows-MCP is added to MCP Registry
- Try out 🪟Windows-Use!!, an agent built using Windows-MCP.
- Windows-MCP is now featured as Desktop Extension in
Claude Desktop.
Supported Operating Systems
- Windows 7
- Windows 8, 8.1
- Windows 10
- Windows 11
🎥 Demos
https://github.com/user-attachments/assets/d0e7ed1d-6189-4de6-838a-5ef8e1cad54e
https://github.com/user-attachments/assets/d2b372dc-8d00-4d71-9677-4c64f5987485
✨ 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 0.7 to 2.5 secs, and may slightly vary based on the number of active applications and system load, also the inferencing speed of the llm.
🛠️Installation
Prerequisites
- Python 3.13+
- UV (Package Manager) from Astra, install with
pip install uvorcurl -LsSf https://astral.sh/uv/install.sh | sh Englishas the default language in Windows highly preferred or disable theLaunch-ToolandSwitch-Toolin the MCP Server for Windows with other languages.
- Install Claude Desktop and
npm install -g @anthropic-ai/dxt
- Clone the repository.
git clone https://github.com/CursorTouch/Windows-MCP.git
cd Windows-MCP
- Build Desktop Extension
DXT:
npx @anthropic-ai/dxt pack
- Open Claude Desktop:
Go to Settings->Extensions->Advance Settings->Install Extension (locate the .dxt file)-> Install
- Enjoy 🥳.
For additional Claude Desktop integration troubleshooting, see the MCP documentation. The documentation includes helpful tips for checking logs and resolving common issues.
-
Install Perplexity Desktop:
-
Clone the repository.
git clone https://github.com/CursorTouch/Windows-MCP.git
cd Windows-MCP
- Open Perplexity Desktop:
Go to Settings->Connectors->Add Connector->Advanced
- Enter the name as
Windows-MCP, then paste the following JSON in the text area.
{
"command": "uv",
"args": [
"--directory",
"<path to the windows-mcp directory>",
"run",
"main.py"
]
}
- Click
Saveand Enjoy 🥳.
For additional Claude Desktop integration troubleshooting, see the Perplexity MCP Support. The documentation includes helpful tips for checking logs and resolving common issues.
- Install Gemini CLI:
npm install -g @google/gemini-cli
- Clone the repository.
git clone https://github.com/CursorTouch/Windows-MCP.git
cd Windows-MCP
-
Navigate to
%USERPROFILE%/.geminiin File Explorer and opensettings.json. -
Add the
windows-mcpconfig in thesettings.jsonand save it.
{
"theme": "Default",
...
//MCP Server Config
"mcpServers": {
"windows-mcp": {
"command": "uv",
"args": [
"--directory",
"<path to the windows-mcp directory>",
"run",
"main.py"
]
}
}
}
- Rerun Gemini CLI in terminal. Enjoy 🥳
npm install -g @qwen-code/qwen-code@latest
- Clone the repository.
git clone https://github.com/CursorTouch/Windows-MCP.git
cd Windows-MCP
-
Navigate to
%USERPROFILE%/.qwen/settings.json. -
Add the
windows-mcpconfig in thesettings.jsonand save it.
{
//MCP Server Config
"mcpServers": {
"windows-mcp": {
"command": "uv",
"args": [
"--directory",
"<path to the windows-mcp directory>",
"run",
"main.py"
]
}
}
}
- Rerun Qwen Code in terminal. Enjoy 🥳
npm install -g @openai/codex
- Clone the repository.
git clone https://github.com/CursorTouch/Windows-MCP.git
cd Windows-MCP
-
Navigate to
%USERPROFILE%/.codex/config.toml. -
Add the
windows-mcpconfig in theconfig.tomland save it.
[mcp_servers.windows-mcp]
command="uv"
args=[
"--directory",
"<path to the windows-mcp directory>",
"run",
"main.py"
]
- Rerun Codex CLI in terminal. Enjoy 🥳
🔨MCP Tools
MCP Client 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 default language, browser, active apps and interactive, textual and scrollable elements along with screenshot of the desktop.Resize-Tool: Used to change the window size or location of an app.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.
🤝 Connect with Us
Stay updated and join our community:
-
📢 Follow us on X for the latest news and updates
-
💬 Join our Discord Community
Star History
⚠️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.
📝 Limitations
- Selecting specific sections of the text in a paragraph, as the MCP is relying on a11y tree. (⌛ Working on it.)
Type-Toolis meant for typing text, not programming in IDE because of it types program as a whole in a file. (⌛ Working on it.)- This MCP server can't be used to play video games.
🪪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 CursorTouch
Citation
@software{
author = {CursorTouch},
title = {Windows-MCP: Lightweight open-source project for integrating LLM agents with Windows},
year = {2024},
publisher = {GitHub},
url={https://github.com/CursorTouch/Windows-MCP}
}
Windows MCP Reviews
Login Required
Please log in to share your review and rating for this MCP.
Actions
Windows MCP's Information
- Author
- CursorTouch
- Category
- Workflow & Automation
- Language
- Python
- License
- MIT License
- Stars
- 3,122
- Updated
- 12 days ago
Configuration
{
"mcpServers": {
"windows-mcp": {
"command": "uv",
"args": [
"--directory",
"<path-to-windows-mcp>",
"run",
"main.py"
],
"env": {}
}
}
}Claude Code (Terminal)
claude mcp add windows-mcp uv --directory <path-to-windows-mcp> run main.pyConfigure Clients
Similar MCP Servers like Windows MCP
Explore related MCPs that share similar capabilities and solve comparable challenges
Activepieces
by activepieces
A self‑hosted, open‑source platform that provides a no‑code builder for creating, versioning, and running AI‑driven automation workflows. Pieces are TypeScript‑based plugins that become MCP servers, allowing direct consumption by large language models.
Skyvern
Officialby Skyvern-AI
Automates browser‑based workflows by leveraging large language models and computer‑vision techniques, turning natural‑language prompts into fully functional web interactions without writing custom scripts.
BlenderMCP
Officialby ahujasid
Enables Claude AI to control Blender for prompt‑assisted 3D modeling, scene creation, and manipulation via a socket‑based Model Context Protocol server.
Pipedream
by PipedreamHQ
Connect APIs quickly with a free, hosted integration platform that enables event‑driven automations across 1,000+ services and supports custom code in Node.js, Python, Go, or Bash.
Inbox Zero
by elie222
Organizes email inbox, drafts replies in the user's tone, tracks follow‑ups, and provides analytics to achieve inbox zero quickly.
Cursor Talk To Figma
by grab
Enables Cursor AI to read and programmatically modify Figma designs through a Model Context Protocol integration.
Ableton MCP
by ahujasid
Enables Claude AI to control Ableton Live in real time, allowing AI‑driven creation, editing, and playback of tracks, clips, instruments, and effects through a socket‑based server.
N8n Mcp Server
by leonardsellem
Provides tools and resources to enable AI assistants to manage and execute n8n workflows via natural language commands.
Gmail AutoAuth MCP Server
by GongRzhe
Provides a Model Context Protocol server that enables AI assistants to send, read, search, and organize Gmail messages, supporting attachments, label and filter management, and automatic OAuth2 authentication.