MCPs tagged with GUI Automation
-
omniparser-autogui-mcp
Automated GUI analysis and interaction via the Model Context Protocol.
omniparser-autogui-mcp is an MCP server that leverages OmniParser to analyze on-screen content and perform automated GUI operations. It integrates with clients such as Claude Desktop and can be configured via a detailed environment setup. The tool supports Windows and can delegate OmniParser processing to external devices, offering flexibility for complex contexts. Multiple environment variables allow customization of backend processing, target window selection, and communication methods, including SSE.
- ⭐ 58
- MCP
- NON906/omniparser-autogui-mcp
-
ScreenPilot
Empower LLMs with full device control through screen automation.
ScreenPilot provides an MCP server interface to enable large language models to interact with and control graphical user interfaces on a device. It offers a comprehensive toolkit for screen capture, mouse control, keyboard input, scrolling, element detection, and action sequencing. The toolkit is suitable for automation, education, and experimentation, allowing AI agents to perform complex operations on a user’s device.
- ⭐ 50
- MCP
- Mtehabsim/ScreenPilot