Awesome MCP › Desktop Automation
CodeRunner is a Model Context Protocol (MCP) server designed to securely execute AI-generated code locally on macOS systems using Apple's container technology. It provides a sandboxed environment that isolates the execution of code, ensuring that the host system and files outside the sandbox remain protected. This setup enables users to process local files such as videos, images, documents, and data with remote large language models (LLMs) like Claude or ChatGPT without the need to upload sensitive files to the cloud, thereby enhancing privacy and security. The primary use case of CodeRunner is to allow LLMs to generate code that runs directly on the user's machine to analyze, transform, or process local files. This eliminates the traditional need for manual code execution, cloud file uploads, and complex environment management. CodeRunner comes with a pre-configured environment and tools within the sandbox, automatically installing additional dependencies as needed, which streamlines the workflow for users. CodeRunner supports multiple integration options, including integration with Claude Desktop, OpenAI's Python agents library, and Google's Gemini CLI. These integrations allow seamless communication between AI models and the local execution environment via the MCP server. The architecture consists of a sandbox container with a Jupyter kernel for isolated code execution and an MCP server that manages communication between the AI models and the sandbox. Security is a key feature, with VM-level isolation provided by Apple's container technology, minimizing resource utilization and attack surface. The project includes example configurations and scripts to help users quickly set up and start using CodeRunner. It is targeted at macOS users with Apple Silicon (M1/M2/M3/M4) and requires Python 3.10 or higher. Overall, CodeRunner enhances the capabilities of remote LLMs by enabling private, efficient, and secure local execution of AI-generated code, making it a valuable tool for users who need to process sensitive local data with AI assistance.
https://github.com/BandarLabs/coderunner
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.
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.