PyMCPAutoGUI 🖱️⌨️🖼️ - GUI Automation via MCP

Name: PyMCPAutoGUI 🖱️⌨️🖼️ - GUI Automation via MCP
Author: kitfactory

@kitfactory

Repository

About PyMCPAutoGUI 🖱️⌨️🖼️ - GUI Automation via MCP

GUI manipulation MCP server

#gui-automation #mcp #python

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "PyMCPAutoGUI": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is PyMCPAutoGUI 🖱️⌨️🖼️ - GUI Automation via MCP?

PyMCPAutoGUI bridges AI agents (e.g., in Cursor or other MCP-compatible environments) with the computer’s graphical user interface. It lets an agent see the screen, control the mouse and keyboard, and interact with windows — just like a human user.

How to use PyMCPAutoGUI 🖱️⌨️🖼️ - GUI Automation via MCP?

Install via pip install pymcpautogui in a Python 3.11+ virtual environment. Run python -m pymcpautogui.server to start the MCP server (defaults to port 6789). Connect from Cursor by adding the provided JSON configuration to mcp.json; then use @PyMCPAutoGUI in chats to invoke tools like move_to, write, screenshot, or activate_window.

Key features of PyMCPAutoGUI 🖱️⌨️🖼️ - GUI Automation via MCP

Empowers AI agents to control any desktop application.
Simple plug‑and‑play integration with MCP‑compatible clients.
Comprehensive mouse, keyboard, and window automation functions.
Screen perception: take screenshots and locate images on screen.
Window management: move, resize, minimize, maximize, restore, close.
User interaction: display alert

Comments

Basic information

More Productivity MCP servers

OmniSocials

Official OmniSocials MCP server — schedule and publish posts, stories, and reels across 11 platforms (Instagram, Facebook, LinkedIn, YouTube, TikTok, X, Pinterest, Bluesky, Threads, Mastodon, Google Business), plus media

Contio MeetingOS

Andrew Ely

Contio MeetingOS is an AI-powered workspace for meeting-driven teams. — from planning to follow-through. It gives you a structured workspace to build agendas, collaborate with participants in real time, capture transcri

YouTube Transcript AI

youtube-transcript.ai

Fetch the full transcript of any YouTube video as clean text — no API key, no signup, no quota wall. Pass a YouTube URL (watch, youtu.be, shorts, embed) or a bare video ID and get the transcript back with title and metad

Sitespeak Claude Plugin

sitespeakai

Manage your SiteSpeakAI chatbot from Claude Code - a plugin and MCP server for optimizing chatbots in plain English.

One

Connect your agent to the apps your team already uses: Gmail, Slack, Stripe, Shopify, HubSpot, Notion, Linear, Salesforce, QuickBooks and more. One hosted MCP server with OAuth sign-in, nothing to install and no API keys