Awesome MCP › Desktop Automation
Peekaboo is a macOS-exclusive utility designed to facilitate the capture and AI-driven analysis of screenshots through a Model Context Protocol (MCP) server and a command-line interface (CLI) tool. It enables AI agents to visually interpret screen content, making it highly useful for visual question answering and automation tasks. The project supports lightning-fast screenshot capture of entire screens, specific applications, or individual windows without disrupting the user's workflow or changing window focus. It integrates with advanced AI vision models such as GPT-4 Vision, Claude, and local AI models via Ollama, providing powerful image analysis capabilities that can answer questions about the visual content or automate tasks based on the analysis. Peekaboo offers two main modes of operation: a standalone CLI tool recommended for most users, which is ideal for command-line workflows, automation, shell scripting, and system administration; and an MCP server mode designed for integration with AI assistants like Claude Desktop and Cursor IDE. This dual functionality allows Peekaboo to serve both individual users and AI-driven applications requiring visual context. The tool includes features for managing windows and applications with smart fuzzy matching, ensuring precise screenshot targeting. It emphasizes privacy by supporting local AI options and operates non-intrusively. Users can configure the tool through a persistent JSON configuration file or environment variables, specifying AI providers, API keys, default save paths, logging preferences, and more. Peekaboo supports common workflows such as capturing and analyzing screenshots in a single command, monitoring active window changes, and batch processing images for AI summarization. The MCP server exposes commands for capturing images, listing applications and windows, and analyzing images with AI vision models, making it a versatile tool for enhancing AI agents' visual understanding on macOS. Overall, Peekaboo bridges the gap between visual content on macOS screens and AI comprehension, enabling sophisticated visual question answering and automation through a seamless MCP interface and CLI tool.
https://github.com/steipete/Peekaboo
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.
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.