Awesome MCP › Desktop Automation
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.
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.
iterm-mcp is a Model Context Protocol server that enables AI models to interact with and control an iTerm terminal session for enhanced REPL and CLI assistance.
An open-source MCP server enabling autonomous AI agents to fully control remote macOS systems through Claude Desktop without extra API keys or software installations.
An MCP server that executes AppleScript to provide full control and automation of Mac applications and system features through simple and minimal setup.
OpenSkills enables running Claude Skills locally on Apple Silicon Macs in a secure, sandboxed environment compatible with MCP tools, ensuring privacy and extensibility.
Automation MCP is a Model Context Protocol server that enables AI models to perform comprehensive desktop automation on macOS, including mouse, keyboard, screen, and window management.
applescript-mcp is a Model Context Protocol server that enables AI applications to interact with macOS through AppleScript, providing extensive control over system functions, files, notifications, and more.
mcp-everything-search is a cross-platform MCP server that provides fast and versatile file searching capabilities by integrating platform-specific search tools like Everything SDK, mdfind, and locate into the MCP ecosystem.
An MCP server that enables AI assistants like Claude to safely control and automate Apple Shortcuts on macOS.
MoLing is a dependency-free, cross-platform MCP server that acts as a local office AI assistant by enabling system and browser interactions and supporting multiple MCP clients.
mcp-ical is an MCP server that enables natural language interaction with macOS Calendar for creating, managing, and querying events through conversational commands.
MCPControl is a Windows server implementing the Model Context Protocol to enable AI-driven programmatic control of mouse, keyboard, windows, screen capture, and clipboard operations for automation and experimentation.
An MCP server that enables Large Language Models to control iOS simulators through natural language commands for comprehensive simulator and app management, UI interaction, and debugging.
Node MCP server that lets AI assistants list tmux sessions, windows and panes, capture pane content, run commands and manage the session layout.
Python MCP server that controls an Android phone over ADB, exposing calls, SMS, contacts, app launching, screenshots, screen recording and UI inspection and automation as tools.
macOS MCP server in TypeScript that exposes Apple Reminders and Calendar through EventKit, with full CRUD over reminders, lists, subtasks and events plus multi-criteria filtering and timezone aware dates.
An MCP server that enables large language models to list, open, and run Siri Shortcuts on macOS through the Model Context Protocol.
MCP server that runs allowlisted shell commands as argv without shell interpretation, with stdin support, timeouts, output caps, a minimal child environment and structured audit logs.
Go CLI and MCP server from Babel Cloud that gives AI agents controllable Android devices and Linux desktop or browser environments, either in the cloud or on a registered local phone.
A Python MCP server that runs whitelisted shell commands inside a restricted directory, enforcing flag allowlists, path-traversal checks, shell-operator blocking, length limits and execution timeouts.
MCP server that runs CMD and shell commands on Windows and Linux and opens SSH connections, built on the official MCP SDK and installable from npm as server-cmd or automatically through Smithery.