
NutJS Windows Control
Cross-platform MCP server for OS automation. Contribute to Cheffromspace/MCPControl development by creating an account on GitHub.
Cheffromspace
README
MCPControl
A cross-platform control server for the Model Context Protocol (MCP), providing programmatic control over system operations including mouse, keyboard, window management, and screen capture functionality. Built on nut.js.
I developed this project as an experiment a few months ago, wanting to see if Claude could play some video games. After seeing it work, I was impressed but set it aside. Recently, it's gained attention from the community, prompting me to resume development. While currently in pre-release state, I'm actively working toward a stable version. If you encounter any issues, please submit them through the issue tracker.
Note: This project aims to support Windows, Linux, and macOS. While most testing has been performed on Windows, cross-platform compatibility contributions are welcome.
⚠️ IMPORTANT DISCLAIMER
THIS SOFTWARE IS EXPERIMENTAL AND POTENTIALLY DANGEROUS
By using this software, you acknowledge and accept that:
- Giving AI models direct control over your computer through this tool is inherently risky
- This software can control your mouse, keyboard, and other system functions which could potentially cause unintended consequences
- You are using this software entirely at your own risk
- The creators and contributors of this project accept NO responsibility for any damage, data loss, or other consequences that may arise from using this software
- This tool should only be used in controlled environments with appropriate safety measures in place
USE AT YOUR OWN RISK
Features
-
Window Management
- List all windows
- Get active window information
- Get window titles
- Get window size and position
- Focus windows
- Resize windows
- Reposition windows
-
Mouse Control
- Mouse movement
- Click operations
- Scroll functionality
- Drag operations
- Cursor position tracking
-
Keyboard Control
- Text input
- Key combinations
- Key press/release operations
- Hold key functionality
-
Screen Operations
- Screen capture
- Screen size retrieval
- Active window detection
-
Clipboard Integration
- Get clipboard content
- Set clipboard content
- Clear clipboard
- Check clipboard state
Installation
- Clone the repository:
git clone https://github.com/Cheffromspace/MCPControl.git
cd MCPControl
- Build the project (this will handle libnut-core and all dependencies):
# Install dependencies
npm install
# Build everything including libnut-core
npm run build:all
For manual building, you can still follow these steps:
# Install cmake-js globally (required for building)
npm install -g cmake-js
# Clone libnut repository directly in the project directory
git clone https://github.com/nut-tree/libnut.git libnut-core
cd libnut-core
# Install dependencies and build
npm install
cmake-js rebuild
# Return to the main project
cd ..
# Build MCPControl
npm run build
Running Tests
Run all tests:
npm test
Generate coverage report:
npm run test:coverage
MCP Server Configuration
To use this project with Claude, add the following configuration to your MCP servers:
{
"mcpServers": {
"MCPControl": {
"command": "C:\\Program Files\\nodejs\\node.exe",
"args": [
"[INSTALL LOCATION]\\MCPControl\\build\\index.js"
]
}
}
}
After configuring your MCP server, restart Claude to see the MCPControl service in the menu.
Project Structure
/src
/handlers
- Request handlers and tool management/tools
- Core functionality implementations/types
- TypeScript type definitionsindex.ts
- Main application entry point
Dependencies
- @modelcontextprotocol/sdk - MCP SDK for protocol implementation
- @nut-tree/libnut - Core native UI automation library
- clipboardy - Cross-platform clipboard handling
- express - Web server framework
- jimp & sharp - Image processing
Testing
The project currently includes unit tests for core functionality. The following test areas are planned for future development:
- Integration tests for cross-module functionality
- Performance testing
- Error handling validation
Known Limitations
- Window minimize/restore operations are currently unsupported in libnut-core
- Advanced screen information (multiple monitors, DPI settings) is limited to main display
- Some operations may require elevated permissions depending on the target application
- Cross-platform support (Linux/macOS) is untested
Contributing
See CONTRIBUTING.md
License
This project is licensed under the MIT License - see the LICENSE file for details.
References
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
AIO-MCP Server
🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from
React MCP
react-mcp integrates with Claude Desktop, enabling the creation and modification of React apps based on user prompts
Atlassian Integration
Model Context Protocol (MCP) server for Atlassian Cloud products (Confluence and Jira). This integration is designed specifically for Atlassian Cloud instances and does not support Atlassian Server or Data Center deployments.

Any OpenAI Compatible API Integrations
Integrate Claude with Any OpenAI SDK Compatible Chat Completion API - OpenAI, Perplexity, Groq, xAI, PyroPrompts and more.
MySQL Server
Allows AI assistants to list tables, read data, and execute SQL queries through a controlled interface, making database exploration and analysis safer and more structured.
Browser Use (used by Deploya.dev)
AI-driven browser automation server that implements the Model Context Protocol to enable natural language control of web browsers for tasks like navigation, form filling, and visual interaction.
Aindreyway Codex Keeper
Serves as a guardian of development knowledge, providing AI assistants with curated access to latest documentation and best practices.