Awesome MCP › Desktop Automation
CMD MCP Server is a Model Context Protocol server that lets an MCP client run command-line operations on the host machine. It executes CMD commands on Windows and shell commands on Linux, and it can also open SSH connections, so a model working through a compatible client can drive both the local terminal and a remote host. The implementation is TypeScript compiled to JavaScript and is built on the official MCP SDK, with glob and zod-to-json-schema as its other runtime dependencies. Node.js version 16 or newer is recommended. Installation is either automatic through Smithery, which writes the Claude Desktop configuration with a single npx command, or manual with npm install server-cmd. The package also exposes a small programmatic API: importing MCPCmdServer from server-cmd, constructing it with an optional configuration object and calling start begins serving, and the README notes that configuration can come from environment variables or from that object, though it leaves the specific options unlisted. For development the repository documents the usual clone, npm install and npm run build cycle, where build compiles TypeScript to JavaScript and prepare packages the module for publishing. The README is explicit that this class of server is risky: executing command-line operations can be dangerous, and anyone deploying it in production is expected to add their own security measures and input validation, since the server itself does not describe a permission model, a command allowlist or a sandbox. That places it in the same family as other shell-execution servers, useful for automating local tasks, builds and remote administration, but only appropriate where the client and its operator are trusted. The project is MIT licensed and directs bug reports and feature requests to the GitHub issue tracker.
https://github.com/PhialsBasement/CMD-MCP-Server
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.