Awesome MCP › Desktop Automation
Windows-MCP is a lightweight, open-source MCP (Model Context Protocol) server designed specifically for seamless integration between AI agents, particularly large language models (LLMs), and the Windows operating system. It acts as a bridge that enables AI agents to interact natively with Windows UI elements, allowing them to perform a variety of tasks such as file navigation, application control, user interface interaction, and quality assurance testing. The project supports Windows versions from 7 through 11 and is built to work with any LLM without relying on traditional computer vision techniques or specialized fine-tuned models, which simplifies setup and reduces complexity. Key features of Windows-MCP include a rich toolset for UI automation, such as tools for keyboard and mouse operations, capturing window and UI states, and executing PowerShell commands. It supports real-time interaction with typical latency between actions ranging from 1.5 to 2.3 seconds, depending on system load and LLM inference speed. The project is open-source under the MIT license, with minimal dependencies, making it easy to set up and customize. Users can extend or adapt the tools to meet specific automation or AI integration needs. Installation requires Python 3.13 or higher, the Anthropic Claude Desktop app or other MCP clients, and additional packages like UV and DXT for desktop extension. The project provides detailed instructions for cloning the repository, building the desktop extension, and integrating with Claude Desktop. It includes a variety of MCP tools such as Click-Tool, Type-Tool, Clipboard-Tool, Scroll-Tool, Drag-Tool, Move-Tool, Shortcut-Tool, Key-Tool, Wait-Tool, State-Tool, Screenshot-Tool, Launch-Tool, Shell-Tool, and Scrape-Tool, enabling comprehensive control over Windows environments. Windows-MCP is intended for users who want to leverage AI agents to automate and interact with Windows systems efficiently and flexibly. It is particularly useful for developers and researchers working on AI-driven automation and integration with desktop environments. The project emphasizes caution due to its direct interaction with the operating system and notes some current limitations, such as text selection within paragraphs and typing in IDEs, which are under development.
https://github.com/CursorTouch/Windows-MCP
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.
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.
Windows-only MCP server in C# that drives the real Microsoft Excel application through its COM API, exposing 26 tools and 234 operations for Power Query, DAX, PivotTables, charts, VBA and formatting.