Awesome MCP › Desktop Automation
The project "mediar-ai/terminator" is a powerful automation tool designed primarily for Windows computers, enabling developers and teams to create and run automations across any desktop application or browser. It is described as a playwright for Windows, focusing on deterministic and efficient automation workflows that run significantly faster than other AI agents like ChatGPT Agents or Claude. The project emphasizes a high success rate of over 95%, achieved by pre-training workflows as deterministic code and only invoking AI for recovery when necessary. This approach reduces complexity and enhances reliability compared to traditional robotic process automation (RPA) tools. Terminator offers a comprehensive platform that includes a CLI, MCP agent, and various libraries supporting multiple programming languages such as Python, TypeScript, and Rust. It supports core automation features like element locators, UI actions (click, type), application and window management, and advanced capabilities including browser automation, workflow recording, multi-display support, and screen capture. While Windows is the primary platform with full feature support, macOS and Linux have partial or experimental support. The project integrates with the Model Context Protocol (MCP), allowing AI assistants to control desktops and automate tasks seamlessly. It provides easy installation methods, including npm and bunx for Windows and source compilation for macOS and Linux. Terminator also offers a public beta workflow builder and managed hosting for teams to record, map, and deploy workflows without requiring technical skills. Overall, Terminator aims to democratize AI-powered desktop automation by providing an open-source, MIT-licensed solution that eliminates the need for managing complex infrastructure or legacy RPA systems. It is suitable for developers seeking to build robust automation workflows and teams looking to streamline repetitive tasks efficiently.
https://github.com/mediar-ai/terminator
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.
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.
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.