Awesome MCP › Desktop Automation
Apple Events MCP Server is a Model Context Protocol server that gives assistants native access to Apple Reminders and Calendar on macOS. It offers full create, read, update and delete support for reminders, checklist subtasks, reminder lists and calendar events. Reminders carry priority levels of high, medium, low or none, tags, and subtasks with progress tracking. Reads can be narrowed with multiple criteria at once: completion state, a due date range, priority, tags, full text search, recurring status and location. Dates are accepted in several formats, including plain dates, date with time, and ISO 8601, and are handled with timezone awareness. Values set inside Reminders.app or Calendar.app round trip through the read responses because the integration goes through EventKit rather than scripting. The EventKit backend is a separate Swift command line tool called event, vendored as a git submodule and compiled into bin/event during install, so no extra Homebrew package is required; the published npm package ships a prebuilt universal signed binary, which means npx users need neither Xcode nor a Swift toolchain. Permissions are handled deliberately: the event binary embeds its own Info.plist and privacy strings and is spawned through a shim that disclaims TCC responsibility, so macOS attributes the prompt to event itself and one grant covers every MCP client on the machine. The README documents recovery from a stuck TCC state with tccutil, a fix for Calendar read errors requiring Full Calendar Access, and a Swift 6.3 requirement on macOS 26. Headless or launchd runs cannot show a permission dialog, so calls that exceed a timeout are killed and return a readable error, tunable through EVENTKIT_CLI_TIMEOUT_MS. It requires Node.js 20 or later and macOS, and is configured in Cursor, ChatWise or Claude Desktop through npx.
https://github.com/FradSer/mcp-server-apple-reminders
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.