PyAutoGUI
Enables AI agents to automate desktop tasks by controlling mouse, keyboard, and screen interactions.
关于
PyAutoGUI provides an MCP (Model Context Protocol) server that allows AI systems to interact with and automate tasks on a computer. It offers functionality for controlling the mouse, simulating keyboard input, capturing screenshots, and retrieving information about the screen and operating system. The server communicates over `stdio` using JSON-RPC, providing a simple and reliable interface for integrating desktop automation into AI workflows.
主要功能
- Capture screenshots and retrieve mouse position
- Simulate keyboard input (single keys, text, hotkeys)
- Retrieve screen size and pixel color
- Control mouse movements, clicks, and drags
- Consistent error handling
- 0 GitHub stars
使用案例
- Enabling AI agents to interact with graphical user interfaces
- Automating repetitive tasks on a desktop
- Integrating desktop automation into AI workflows
Sponsored