Pymcpautogui

🚀 PyMCPAutoGUI 🖱️⌨️🖼️ - GUI Automation via MCP

Elevate the capabilities of your AI agents! ✨ PyMCPAutoGUI bridges the gap between your AI agents (such as Cursor or other MCP-compatible environments) and your computer's graphical user interface (GUI). It empowers your agents to see the screen 👁️, control the mouse 🖱️ and keyboard ⌨️, and interact with windows 🪟, just like a human user!

Say goodbye to tedious manual GUI tasks and let your AI take on the heavy lifting 💪. Perfect for automating repetitive actions, testing GUIs, or building powerful AI assistants 🤖.

🚀 Quick Start

PyMCPAutoGUI enables your AI agents to interact with the GUI directly. With simple server commands, you can start leveraging its capabilities right away.

✨ Features

Why Choose PyMCPAutoGUI?

• 🤖 Enhance Your Agents: Empower your AI agents to interact directly with desktop applications.
• ✅ Easy Integration: Seamlessly integrate with MCP clients like the Cursor editor. Plug and play!
• 🚀 User-Friendly: Start with simple server commands. It's really that easy!
• 🖱️⌨️ Comprehensive Control: Offers most of the features from the proven PyAutoGUI and PyGetWindow.
• 📄 License: This project is licensed under the MIT License - see the LICENSE file for details.

Feature Highlights

• Supports agents to directly call the functions of PyAutoGUI and PyGetWindow via the MCP protocol.
• Completely non-intrusive design without modifying the underlying libraries.
• Supports multi-threaded processing for stable operation.
• Provides detailed logging and error handling mechanisms.
• Supports custom configuration to meet different needs.

📦 Installation

pip install pymcpautogui

🔧 Configuration Options

PyMCPAutoGUI provides the following configurable parameters:

💻 Usage Examples

Basic Usage

In an MCP-compatible client:

# Basic mouse operations
@PyMCPAutoGUI move_to(x=100, y=200)
@PyMCPAutoGUI click(button='left')
@PyMCPAutoGUI drag_to(x=300, y=400)

# Keyboard input examples
@PyMCPAutoGUI write(text='Hello AI!', interval=0.1)
@PyMCPAutoGUI hotkey('ctrl', 'c')

# Window management
@PyMCPAutoGUI get_all_titles
@PyMCPAutoGUI activate_window(title='Notepad')
@PyMCPAutoGUI minimize_window()

# Screenshot function
@PyMCPAutoGUI screenshot(filename='snapshot.png')

📄 License

This project is licensed under the MIT License. For more details, please refer to the LICENSE file.

Let your AI agents interact with the computer more intelligently through PyMCPAutoGUI! 😄