Awesome MCP › Desktop Automation
Docker-Android is a set of Docker images that run Android emulators for application development and testing, covering native, web and hybrid apps. Each image bundles an emulator for a specific Android version and device profile, from a Nexus One up to a Galaxy S10 and several tablets, and exposes it over VNC so the emulator screen can be viewed from outside the container. The project supports controlling the emulator remotely through adb connect, sharing container logs through a web UI, integrating with Genymotion Cloud as an alternative emulator backend, and running UI test frameworks such as Appium and Espresso against the emulated devices; the images can also build Android projects and run unit tests. Alongside these established images, the project ships a beta docker-android:mcp image and a Python package under the repository's mcp/ directory, with modules for the server, device handling and adb access, that exposes emulator and ADB operations as MCP tools so an MCP-aware AI agent can drive an Android emulator the way a human tester would through adb. The core project predates MCP and is primarily an Android emulation and CI testing tool; the MCP server is one of several ways to interact with it, alongside the web VNC viewer and direct adb access. It targets mobile developers and QA engineers who need reproducible, containerized Android environments for automated testing pipelines, and, through the MCP image, users who want an AI agent to operate an Android emulator for exploratory testing or automation. The project has an established donation link and community chat channel, indicating maintenance that predates its MCP support.
https://github.com/budtmo/docker-android
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.
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.
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.