Awesome MCP › Desktop Automation
cli-mcp-server is a Python MCP server that gives an LLM application controlled access to a command line. It exposes two tools: run_command, which executes a single whitelisted command inside an allowed directory, and show_security_rules, which reports the active configuration, namely the working directory, the allowed commands and flags, and the maximum command length and timeout, so the host can see what it is permitted to do. Behaviour is set entirely through environment variables. ALLOWED_DIR is required and fixes the base directory for execution. ALLOWED_COMMANDS and ALLOWED_FLAGS take comma-separated lists and default to ls, cat, pwd and to -l, -a, --help respectively, with the literal value all available to lift either restriction. MAX_COMMAND_LENGTH caps the command string at 1024 characters by default, COMMAND_TIMEOUT stops execution after 30 seconds by default, and ALLOW_SHELL_OPERATORS, disabled by default, decides whether operators such as and, or, pipes and redirection are accepted. The security model combines command and flag whitelisting with path normalisation and traversal prevention, symlink resolution and validation, working-directory restriction, shell-operator injection blocking, length limits and execution timeouts. Failures are reported through distinct error types for security violations, timeouts, invalid command formats, path violations and execution failures, so the caller can tell why a command was refused rather than seeing a generic error. Command execution is asynchronous. Installation is either automatic through Smithery for Claude Desktop or manual, by adding an entry to claude_desktop_config.json that runs the package with uv from a local checkout or with uvx from PyPI, passing all security settings in the env block. Development requires Python 3.10 or newer and the MCP protocol library; the repository documents building and publishing with uv and debugging through the MCP Inspector. The project is MIT licensed.
https://github.com/MladenSU/cli-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.