Awesome MCP › Desktop Automation
OpenSkills is a project designed to run Claude Skills locally on a Mac, specifically leveraging Apple Silicon hardware. Claude Skills are reusable folders containing instructions, scripts, and resources that enhance the capabilities of the Claude AI for specialized tasks. This project enables users to execute these skills entirely on their local machine within a sandboxed environment, ensuring privacy and data security by avoiding any cloud uploads. The tool uses Apple's native container technology to run AI-generated code in an isolated, VM-level sandbox, providing full control and compatibility with various MCP-compatible AI tools such as Claude Desktop, Gemini CLI, Qwen CLI, and others. The project supports processing a wide range of file types including documents, spreadsheets, presentations, images, and more, allowing users to perform tasks like creating presentations from markdown, extracting tables from PDFs, generating ASCII art, filling out tax forms, and batch processing images. It offers extensibility by allowing users to import official skills from Anthropic's skills repository or create their own custom skills following a defined folder structure. Skills can be added by placing them in a specific directory, and the system automatically maps file paths to enable seamless local file access within the containerized environment. OpenSkills is particularly valuable for users who require high privacy standards and want to maintain full control over their data while leveraging advanced AI capabilities. The project includes detailed setup instructions for integrating with various AI clients and provides example use cases and demos to showcase its functionality. It supports Python 3.10+ and requires macOS on Apple Silicon. Overall, OpenSkills bridges the gap between powerful AI skill execution and local data privacy by enabling a fully local, secure, and extensible environment for running Claude Skills.
https://github.com/instavm/open-skills
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.