Awesome MCP › Desktop Automation
MoLing is a dependency-free, cross-platform MCP (Model Context Protocol) server designed to function as a local office AI assistant by enabling system and browser interactions. It supports multiple MCP clients such as Claude, Cline, and Cherry Studio, facilitating seamless integration with various AI platforms that support the MCP protocol. The server operates by leveraging operating system APIs to perform file system operations including reading, writing, merging, statistics, and aggregation, as well as executing system commands directly through a command-line terminal interface. This makes MoLing a powerful tool for local office automation tasks. One of the key advantages of MoLing is its dependency-free nature, which means it requires no additional installations or environment setups like Node.js, Python, or Docker. This ensures compatibility across multiple operating systems including Windows, Linux, and macOS, although it has been primarily tested on macOS. The server also includes browser control capabilities powered by the chromedp library, which requires Chrome browser to be installed and configured, especially on Windows where the full path to Chrome must be set in system environment variables. MoLing offers two operation modes: Stdio mode for interactive command-line use and SSE mode optimized for headless or automated environments. The project provides easy installation options including script-based installation for Linux/MacOS and Windows (though Windows support is not fully tested), direct download of prebuilt binaries, and building from source using the Go toolchain. Configuration is straightforward, with automatic client configuration installation supported for popular MCP clients. The project aims to expand its features in the future to include personal PC data organization, document writing assistance, schedule planning, and life assistant functionalities. Licensed under Apache License 2.0, MoLing is an open-source project focused on enhancing local AI assistant capabilities through the MCP protocol.
https://github.com/gojue/moling
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.