Database · MODEL CONTEXT PROTOCOL
hetaoBackend mcp pyautogui server
A MCP (Model Context Protocol) server that provides automated GUI testing and control capabilities through PyAutoGUI.
连接能力
hetaoBackend mcp pyautogui server 为 AI Agent 提供什么
- Control mouse movements and clicks
- Simulate keyboard input
- Take screenshots
- Find images on screen
- Get screen information
- Cross-platform support (Windows, macOS, Linux)
- Move mouse to specific coordinates
- Click at current or specified position
- Drag and drop operations
- Get current mouse position
- Type text
- Press individual keys
- Hotkey combinations
- Take screenshots
- Get screen size
- Find image locations on screen
- Get pixel colors
- Python 3.12+
- PyAutoGUI
- Other dependencies will be installed automatically
- Sync dependencies and update lockfile:
- Build package distributions:
- Publish to PyPI:
- Token: `--token` or `UV_PUBLISH_TOKEN`
- Username/password: `--username`/`UV_PUBLISH_USERNAME` and `--password`/`UV_PUBLISH_PASSWORD`
安全
MCP 收录不等于安全审核
MCP 服务器可能获得模型上下文、凭据、本地文件或调用外部系统的权限。连接 Agent 前,请检查代码、环境变量、网络行为、软件包来源与维护状态。
README
仓库文档
A MCP (Model Context Protocol) server that provides automated GUI testing and control capabilities through PyAutoGUI.
- Control mouse movements and clicks
- Simulate keyboard input
- Take screenshots
- Find images on screen
- Get screen information
- Cross-platform support (Windows, macOS, Linux)
The server implements the following tools:
- Move mouse to specific coordinates
- Click at current or specified position
- Drag and drop operations
- Get current mouse position
- Type text
- Press individual keys
- Hotkey combinations
- Take screenshots
- Get screen size
- Find image locations on screen
- Get pixel colors
- Python 3.12+
- PyAutoGUI
- Other dependencies will be installed automatically
Install the package:
pip install mcp-pyautogui-serverOn MacOS:
~/Library/Application\ Support/Claude/claude_desktop_config.jsonOn Windows:
%APPDATA%/Claude/claude_desktop_config.jsonDevelopment/Unpublished Servers Configuration:
{
"mcpServers": {
"mcp-pyautogui-server": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-pyautogui-server",
"run",
"mcp-pyautogui-server"
]
}
}
}Published Servers Configuration:
{
"mcpServers": {
"mcp-pyautogui-server": {
"command": "uvx",
"args": [
"mcp-pyautogui-server"
]
}
}
}- Sync dependencies and update lockfile:
uv sync- Build package distributions:
uv build- Publish to PyPI:
uv publishNote: Set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
For the best debugging experience, use the MCP Inspector.
Launch the MCP Inspector via npm:
npx @modelcontextprotocol/inspector uv --directory /path/to/mcp-pyautogui-server run mcp-pyautogui-serverThe Inspector will display a URL that you can access in your browser to begin debugging.
This project is licensed under the MIT License - see the LICENSE file for details.
社区