Awesome MCP › Desktop Automation
GBOX provides sandboxed environments in which AI agents can operate computers and mobile devices. In the mobile scenario an agent uses GBOX to develop and test Android applications or to drive real apps for automation tasks; in the desktop scenario it operates desktop software such as a browser, a terminal or VSCode. The MCP server is one of the supported entry points: plugging the GBOX MCP server into Cursor, Claude Code or another MCP client gives that assistant the ability to control the connected device, and the README notes that MCP control currently covers Android environments only. The MCP server is published on npm as @gbox.ai/mcp-server and is normally wired up by the CLI itself, since gbox mcp export can merge the configuration into Claude Code or Cursor, optionally scoped to a project. The CLI is written in Go, installs via a shell script, Homebrew on macOS or the @gbox.ai/cli npm package on Linux and Windows, and pulls its own dependencies (ADB, frpc, Appium, Node.js) either on demand or through gbox setup. After gbox login, gbox device-connect attaches an Android device. Three kinds of Android environment are offered: a cloud virtual device for testing and development, a cloud physical device that is a real handset intended for production use, and a local physical device registered from your own hardware with developer mode enabled. A Linux desktop and browser environment is also available in the cloud. Alongside the CLI and MCP server the project ships an SDK, and its documentation site covers CLI, SDK and local device registration. Building from source needs Go 1.21 or later, Make, pnpm and Node.js. The code is Apache 2.0 licensed.
https://github.com/babelcloud/gbox
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.