This is an MCP server that analyzes the screen with OmniParser and automatically operates the GUI. Confirmed on Windows. This is MIT license, but Excluding submodules and sub packages. OmniParser's repository is CC-BY-4.0. Each OmniParser model has a different license (reference). 1. Please do the following: (Other than Windows, use export instead of set.) (If you want langchainexample.py to work,
Add this skill
npx mdskills install NON906/omniparser-autogui-mcpEnables vision-powered GUI automation via OmniParser with screen analysis and control capabilities
claude mcp add omniparser-autogui-mcp -- npx -y omniparser-autogui-mcp
npx mdskills install NON906/omniparser-autogui-mcp