Awesome MCP › Desktop Automation
The ios-simulator-mcp project is a Model Context Protocol (MCP) server designed specifically for interacting with iOS simulators. It enables AI-driven control and inspection of iOS simulator user interfaces, facilitating UI testing and quality assurance tasks. The server provides a range of functionalities such as retrieving the ID of the currently booted iOS simulator, describing all accessibility elements on the screen, performing UI interactions like tapping, text input, swiping, and inspecting UI elements at specific coordinates. Additionally, it supports taking screenshots and recording videos of the simulator screen. The project is intended to be used in conjunction with MCP clients, allowing AI assistants to perform automated UI testing and validation by making tool calls through the MCP interface. This is particularly useful for verifying UI consistency and behavior immediately after feature implementation. The server can be configured using environment variables to filter out specific tools if needed. It requires macOS with Xcode and iOS simulators installed, along with the Facebook IDB tool for simulator interaction. Installation instructions are provided for integration with popular MCP clients like Cursor and Claude Code, either by using NPX for quick setup or by cloning the repository for local development. The project emphasizes security by addressing command injection vulnerabilities in versions prior to 1.3.3. Overall, ios-simulator-mcp serves as a powerful tool for developers and QA engineers to automate and streamline the testing of iOS app interfaces within simulators, leveraging AI capabilities through the Model Context Protocol.
https://github.com/joshuayoes/ios-simulator-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.
CLI, C library and MCP server giving AI agents computer use over native desktop apps on macOS, Windows and Linux via the OS accessibility tree, with no screenshots or pixel matching.
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.
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.
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.
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.
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.