What is Python version required?
Python 3.12 or later is required.
@hetaoBackend
基本情報
A MCP (Model Context Protocol) server that provides automated GUI testing and control capabilities through PyAutoGUI.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-pyautogui-server": {
"command": "uv",
"args": [
"sync"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
mcp-pyautogui-server is a Model Context Protocol (MCP) server that provides automated GUI testing and control capabilities through PyAutoGUI. It is intended for developers who need programmatic control of mouse movements, keyboard input, and screen operations across Windows, macOS, and Linux.
Install the package with pip install mcp-pyautogui-server, then add it to your MCP client configuration (e.g., Claude Desktop config) using the published server entry: {"command": "uvx", "args": ["mcp-pyautogui-server"]}. For development, use uv with the local directory path.
Python 3.12 or later is required.
Windows, macOS, and Linux are all supported.
PyAutoGUI and other dependencies are installed automatically when you install the package via pip.
Add the server entry to the Claude Desktop config file (`claude_desktop_config.json`) using `{"command": "uvx", "args": ["mcp-pyautogui-server"]}` for published servers.
Use the MCP Inspector by running `npx @modelcontextprotocol/inspector uv --directory /path/to/mcp-pyautogui-server run mcp-pyautogui-server` and then access the displayed URL in a browser.

Model Context Protocol Servers
Hindsight: Agent Memory That Learns
🚀 The fast, Pythonic way to build MCP servers and clients.
Open-source MCP to use Blender with any LLM

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
コメント