Awesome MCP › Desktop Automation
Phone MCP is a Model Context Protocol plugin, distributed on PyPI as phone-mcp and runnable with uvx, uv or pip, that gives an MCP client control over a connected Android device through ADB. The device needs USB debugging enabled and a working ADB installation on the host; configuration is a standard mcpServers entry for clients such as Claude Desktop, Cursor or Trae. Feature groups documented in the README include telephony (placing and ending calls, handling incoming calls), messaging (sending SMS and reading received and sent messages with pagination), contacts (listing contacts and creating new ones through UI automation), media (screenshots, screen recording, media control), application handling (launching apps by name, by package or by explicit package/activity component, listing installed apps with optional pagination and detail, terminating apps), system information such as window details and app shortcuts, opening URLs in the device browser, and a maps helper that searches nearby points of interest together with their phone numbers. A large part of the tool surface is screen work: a unified screen-interact command performs taps by coordinate, by element text or by content description, swipes, key presses and text input, and finds elements by text, id, class or description. Higher-level helpers wait for an element, scroll until an element is found, produce a structured analysis of the current screen, and monitor the UI over an interval until specified text, an id or a class appears or disappears. The same functionality is available from a phone-cli command line tool, which the README uses for its examples. Requirements are Python 3.7 or newer, ADB tools and a debug-enabled Android device.
https://github.com/hao-cyber/phone-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.