PyMCPAutoGUI
If you are the rightful owner of PyMCPAutoGUI and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
PyMCPAutoGUI is a tool that bridges AI agents with a computer's GUI, enabling automation of tasks like mouse and keyboard control, window management, and screen perception.
PyMCPAutoGUI is a powerful tool designed to enhance AI agents' capabilities by allowing them to interact with a computer's graphical user interface (GUI). It provides a seamless connection between AI agents and desktop applications, enabling the automation of repetitive tasks, GUI testing, and the creation of AI assistants. The tool is compatible with MCP environments like the Cursor editor and offers a wide range of functions for GUI automation, including mouse and keyboard control, window management, and screen perception. PyMCPAutoGUI is easy to integrate and use, requiring only a simple server command to get started. It supports multiple operating systems and Python 3.11+, making it a versatile choice for developers looking to automate GUI tasks.
Features
- Empower Your Agents: Allows AI agents to interact directly with desktop applications.
- Simple Integration: Works seamlessly with MCP-compatible clients like the Cursor editor.
- Comprehensive Control: Offers a wide range of GUI automation functions from PyAutoGUI and PyGetWindow.
- Screen Perception: Includes tools for taking screenshots and locating images on the screen.
- Window Management: Control window position, size, state, and more.
Tools
Mouse
Functions like move_to, click, drag_to, scroll, and more.
Keyboard
Functions like write, press, hotkey, and more.
Screenshots
Functions like screenshot, locate_on_screen, and more.
Windows
Functions like activate_window, minimize_window, and more.
Dialogs
Functions like alert, confirm, and prompt.
