Awesome MCP › Desktop Automation
Desktop Commander MCP is a powerful MCP server designed for integration with Claude, enabling advanced terminal control, file system search, and diff file editing capabilities. It leverages the Model Context Protocol (MCP) to seamlessly integrate AI with system-level operations, providing a comprehensive toolset for developers and users who want to automate and manage their desktop environment through AI-driven commands. The project offers enhanced terminal command execution with interactive process control, allowing users to run code in memory for languages like Python, Node.js, and R without the need to save files. It supports instant data analysis by querying CSV or JSON files directly, and it can interact with running processes such as SSH sessions, databases, and development servers. The server supports output streaming, command timeout, background execution, and process management including listing and killing processes. Desktop Commander MCP also features session management for long-running commands and dynamic server configuration management, enabling users to get and set configuration values and update multiple settings without restarting the server. It provides full filesystem operations such as reading, writing, creating, listing, moving files and directories, searching files, and retrieving file metadata. A unique feature is the ability to read files from the end using negative offsets, similar to the Unix tail command. For code editing, it supports surgical text replacements for small changes, full file rewrites for major edits, multiple file support, and pattern-based replacements. It uses vscode-ripgrep for recursive code or text search within folders. The server maintains comprehensive audit logging with automatic tool call logs, log rotation, detailed timestamps, and argument tracking. Installation is flexible with multiple options including npx, bash script installer for macOS, Smithery integration, manual config addition, and local checkout. Some options support automatic updates while others require manual updates. The project is well-documented with detailed usage instructions, update and uninstall procedures, and community support through Discord and sponsorship options. Overall, Desktop Commander MCP is a robust and versatile MCP server that extends the capabilities of Claude by integrating AI with terminal and filesystem operations, making it an essential tool for AI-driven desktop automation and development workflows.
https://github.com/wonderwhy-er/DesktopCommanderMCP
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.
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.