Awesome MCP › Desktop Automation
MCPControl is a Windows server implementation of the Model Context Protocol (MCP) designed to enable AI-driven programmatic control over various system operations such as mouse movements, keyboard inputs, window management, screen capture, and clipboard operations. This project serves as a bridge between AI models and the Windows desktop environment, allowing secure and automated interaction with the system for purposes like automation, experimentation, and testing. The server supports multiple automation providers including native Windows automation (keysender), PowerShell scripting, and AutoHotkey v2 scripting, offering flexibility for different automation needs. MCPControl is optimized for use in virtual machines with a recommended resolution of 1280x720 to ensure accurate mouse click operations. It supports Server-Sent Events (SSE) transport for network communication and can be configured to run with HTTPS/TLS for secure remote deployments, adhering to MCP specifications. Key features include precise mouse control (movement, clicks, drag, scroll), comprehensive keyboard control (text input, key combos, key press/release, hold key), window management (listing windows, focusing, resizing, repositioning), and screen operations (high-quality screenshots, screen size detection, active window capture). The project is aimed at enabling AI models like Claude to perform tasks such as application testing, workflow automation, form filling, AI gaming, visual reasoning, and human-AI collaboration. MCPControl is experimental software and carries inherent risks as it grants AI models direct control over critical system functions. Users are advised to operate it in controlled environments with appropriate safety measures. The project provides detailed setup instructions, including prerequisites like Visual Studio Build Tools, Python, and Node.js, and offers command-line options for advanced configurations. Overall, MCPControl is a powerful tool for integrating AI with Windows desktop automation through the Model Context Protocol, facilitating innovative AI-driven workflows and experiments.
https://github.com/claude-did-this/MCPControl
UI-TARS Desktop is a cross-platform GUI Agent application that uses a vision-language model to enable natural language control of computers with precise visual recognition and real-time feedback, integrating Model Context Protocol tools for advanced multimodal AI-driven automation.
Docker-Android packages Android emulators in Docker with VNC access, ADB control and log sharing for app testing, plus a beta MCP server image that exposes emulator control to AI agents.
Desktop Commander MCP is an MCP server for Claude that integrates AI with terminal control, file system search, and file editing capabilities, enabling advanced desktop automation and development workflows.
Windows-MCP is a lightweight, open-source MCP server that enables seamless integration and automation between AI agents using LLMs and the Windows operating system, supporting a wide range of UI interactions and system controls.
Peekaboo is a macOS-only MCP server and CLI tool that enables AI agents to capture and analyze screenshots with AI vision models for visual question answering and automation.
ios-simulator-mcp is an MCP server enabling AI-driven interaction, control, and inspection of iOS simulators for automated UI testing and quality assurance.
Terminator is an open-source automation tool for Windows that leverages the Model Context Protocol to enable AI-driven desktop and browser automation with high reliability and speed.
CodeRunner is an MCP server that securely executes AI-generated code locally on macOS using Apple's container technology, enabling private and efficient processing of local files with remote LLMs.