Awesome MCP › Desktop Automation
The project iterm-mcp is a Model Context Protocol (MCP) server designed to enable AI models to interact with and control an iTerm terminal session. This interaction facilitates enhanced REPL (Read-Eval-Print Loop) and CLI (Command Line Interface) assistance by allowing the AI model to inspect terminal output, send commands, and control terminal behavior. The server is optimized for efficient token use by allowing the model to focus only on relevant output, typically the last few lines, even for long-running commands. It provides natural integration where the user shares the iTerm session with the model, enabling the user to ask questions about the terminal screen or delegate tasks to the model, which then performs each step interactively. The model can fully control the terminal, including starting and interacting with REPLs and sending control characters like ctrl-c and ctrl-z. The project emphasizes minimal dependencies and ease of use, runnable via npx, and is designed to integrate smoothly with MCP clients such as Claude Desktop. Safety considerations are highlighted, noting that the user is responsible for monitoring the model's actions and ensuring safe use, as the server does not impose restrictions on command execution. The project requires iTerm2 to be running and Node.js version 18 or greater. Installation instructions include configuration for Claude Desktop on macOS and Windows, and an automated installation option via Smithery. Development instructions cover dependency installation, building, and debugging using the MCP Inspector tool. Overall, iterm-mcp provides a powerful interface for AI models to interact with terminal sessions, enhancing automation and assistance capabilities in command-line environments.
https://github.com/ferrislucas/iterm-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.
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.