MCP SiftCurated directory

mcp-pyautogui-server

by hetaobackend

用于 pyautogui 的 MCP 服务器，提供自动化 GUI 测试和控制功能，包括鼠标和键盘控制、截图以及屏幕信息。需要 Python 3.12+ 和 PyAutoGUI。Claude Desktop 的配置文件位于 macOS 的 '~/Library/Application Support/Claude/claude_desktop_config.json' 和 Windows 的 '%APPDATA%/Claude/claude_desktop_config.json'。

Developer toolsstdioCommunity

Repository-wide counts · Cached 2026-03-07

View on GitHubCheck installation steps

Overview

The mcp-pyautogui-server MCP server is a publicly available project. Review the upstream repository for installation instructions, supported tools, compatibility, permissions, and current maintenance status.

Configuration

Configuration, transport, authentication, and runtime requirements vary by project. Open the repository before connecting and use the smallest set of credentials and permissions required.

Open the mcp-pyautogui-server repository to read the latest documentation.

KEEP EXPLORING

Compare source, connection, and authentication details before choosing an implementation.

View the complete category

模型上下文协议服务器

modelcontextprotocol

Community

一组用于模型上下文协议（MCP）的参考实现，展示了对大型语言模型（LLM）工具和数据源的安全且受控的访问方式。

Developer tools

Context7 Platform - Up-to-date Code Docs For Any Prompt

upstash

Community

Context7 MCP server providing up-to-date, version-specific documentation and code examples for libraries, enabling coding agents to fetch accurate docs and code snippets. Requires an API key for higher rate limits, passed via CONTEXT7_API_KEY header.

Developer tools

Playwright MCP

Microsoft Corporation

Community

A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. Enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.

Developer tools

AIHawk

feder-cr

Community

AIHawk is an anti detect browser and web browsing agent, open source, with an MCP server for coding agents: undetected, no captchas, no blocks. It requires an OpenRouter API key for the standalone web UI mode, which can be provided via the --openrouter-key flag or the OPENROUTER_API_KEY environment variable or a .env file in the running directory.

Developer tools
FROM THE SOURCE

Repository README

Build-time snapshot · Retrieved 2026-10-05

View original

mcp-pyautogui-server

smithery badge

A MCP (Model Context Protocol) server that provides automated GUI testing and control capabilities through PyAutoGUI.

Features

  • Control mouse movements and clicks
  • Simulate keyboard input
  • Take screenshots
  • Find images on screen
  • Get screen information
  • Cross-platform support (Windows, macOS, Linux)

Tools

The server implements the following tools:

Mouse Control

  • Move mouse to specific coordinates
  • Click at current or specified position
  • Drag and drop operations
  • Get current mouse position

Keyboard Control

  • Type text
  • Press individual keys
  • Hotkey combinations

Screen Operations

  • Take screenshots
  • Get screen size
  • Find image locations on screen
  • Get pixel colors

Installation

Prerequisites

  • Python 3.12+
  • PyAutoGUI
  • Other dependencies will be installed automatically

Install Steps

Install the package:

pip install mcp-pyautogui-server

Claude Desktop Configuration

On MacOS:

~/Library/Application\ Support/Claude/claude_desktop_config.json

On Windows:

%APPDATA%/Claude/claude_desktop_config.json

Development/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"
      ]
    }
  }
}

Development

Building and Publishing

  1. Sync dependencies and update lockfile:
uv sync
  1. Build package distributions:
uv build
  1. Publish to PyPI:
uv publish

Note: Set PyPI credentials via environment variables or command flags:

  • Token: --token or UV_PUBLISH_TOKEN
  • Username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

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-server

The Inspector will display a URL that you can access in your browser to begin debugging.

License

This project is licensed under the MIT License - see the LICENSE file for details.