desktop_screenshot_mcp_server

metamintbtc/desktop_screenshot_mcp_server

3.1

If you are the rightful owner of desktop_screenshot_mcp_server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

The Screenshot MCP Server is a modern server built with .NET 10 that simulates Print Screen functionality, enabling AI assistants to capture screenshots on Windows.

Tools
4
Resources
0
Prompts
0

Screenshot MCP Server 📸

A modern Model Context Protocol (MCP) Server for Windows Screenshots built with .NET 10. This server simulates Print Screen functionality and enables AI assistants to capture screenshots.

✨ Features

  • 🖥️ Multi-Monitor Support: Capture all screens simultaneously
  • 🎯 Primary Screen: Screenshots of main display only
  • 📊 Screen Info: Detailed information about all displays
  • 🚀 Print Screen Simulation: Just like the Windows Print Screen key
  • 💾 Desktop Integration: Screenshots saved to Desktop with timestamps
  • State-of-the-Art: Latest .NET 10 technology

🛠️ Installation

⚡ One-Click Install via UVX (Recommended)

Copy this URL and paste it in your browser:

vscode:mcp/install?{"name":"screenshot-mcp-server","gallery":true,"command":"uvx","args":["screenshot-mcp-server"]}

🔧 Manual UVX Installation

# Install UV (if not already installed)
pip install uv

# Run Screenshot MCP Server
uvx screenshot-mcp-server

📦 Alternative: Manual Installation via Git

git clone https://github.com/metamintbtc/desktop_screenshot_mcp_server.git
cd desktop_screenshot_mcp_server
dotnet build

VS Code MCP Configuration

Option A: Traditional mcp.json

Create mcp.json in your workspace or VS Code user directory:

{
  "mcpServers": {
    "screenshot-mcp-server": {
      "command": "dotnet",
      "args": ["run", "--project", "H:\\Screenshot_mcp\\ScreenshotMcpServer.csproj"],
      "description": "Windows Screenshot MCP Server",
      "env": {}
    }
  }
}
Option B: VS Code Settings

Add to your VS Code settings.json:

{
  "github.copilot.chat.mcp.servers": {
    "screenshot-mcp-server": {
      "command": "dotnet",
      "args": ["run", "--project", "H:\\Screenshot_mcp\\ScreenshotMcpServer.csproj"],
      "description": "Windows Screenshot Server"
    }
  }
}

🚀 Usage

In VS Code with GitHub Copilot

Simply ask Copilot in natural language:

  • "Take a screenshot of all my screens"
  • "Capture just the primary monitor"
  • "Show me information about my displays"
  • "Simulate pressing Print Screen"

Available Tools

📸 TakeScreenshot

Captures all screens (simulates Print Screen)

Captures all monitors simultaneously
Saves as PNG to Desktop with timestamp
Filename: screenshot_2025-08-04_18-59-30.png
🎯 TakePrimaryScreenshot

Captures only the primary screen

Captures main monitor only
Perfect for focused screenshots
Filename: primary_screenshot_2025-08-04_18-59-30.png
📊 GetScreenInfo

Shows detailed information about all displays

- Number of monitors
- Resolutions and positions  
- Virtual desktop size
⌨️ SimulatePrintScreen

Emulates exactly the Windows Print Screen key press

💻 System Requirements

  • OS: Windows 10/11 (x64)
  • .NET: .NET 10.0 or higher
  • RAM: Minimum 512 MB
  • Storage: 50 MB free space

🔧 Development

Build

dotnet build ScreenshotMcpServer.csproj

Run

dotnet run --project ScreenshotMcpServer.csproj

Publish

dotnet publish -c Release -o ./dist

📁 Project Structure

screenshot-mcp-server/
├── Program.cs              # Main entry point
├── ScreenshotTool.cs      # Screenshot functionality
├── ScreenshotMcpServer.csproj # .NET project
├── package.json           # NPM configuration
├── README.md             # This file
└── bin/                  # Compiled binaries

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

📄 License

This project is licensed under the MIT License. See for details.

🔗 Links

🆘 Support

For issues or questions:


Made with ❤️ for the AI Community