Awesome MCP › Desktop Automation
The project "applescript-mcp" is a Model Context Protocol (MCP) server designed to enable large language model (LLM) applications to interact seamlessly with macOS through AppleScript. This server provides a standardized interface that allows AI applications to control various macOS system functions, manage files, handle notifications, and more, effectively bridging AI capabilities with native macOS operations. Key features of applescript-mcp include calendar management for creating and listing events and reminders, clipboard operations such as copying, retrieving, and clearing clipboard content, and Finder integration for file selection, searching, and previewing. It also supports system notifications, including sending notifications and toggling Do Not Disturb mode, and system controls like adjusting volume, toggling dark mode, launching and quitting applications, and retrieving the active application. The server extends its functionality to terminal integration with iTerm, allowing commands to be run and clipboard content to be pasted directly into the terminal. It supports automation through macOS Shortcuts, enabling listing and running shortcuts with optional inputs. Email management is facilitated through Mail.app integration, allowing the creation of new emails, listing emails from mailboxes, and retrieving specific emails based on various criteria. Messaging capabilities include listing iMessage and SMS chats, retrieving messages, searching messages by text, sender, or chat, and composing messages with options for auto-sending. The project also supports note-taking with formatted notes creation, listing, and searching, as well as document creation in Pages. Planned features aim to expand support to Safari for web browsing control and enhanced reminders management. The project requires macOS 10.15 or later and Node.js 18 or later to operate. Overall, applescript-mcp serves as a powerful MCP server that empowers AI applications to interact deeply with macOS environments, leveraging AppleScript to provide extensive control over system and application functionalities, making it a valuable tool for developers building AI-driven macOS integrations.
https://github.com/joshrutkowski/applescript-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.