Analyzes images and video and runs object detection with Google Gemini or Vertex AI, for UI review and visual regression checks.
Setup
This project documents no single launch command; follow its repository instructions.
AI Vision MCP
tan-yong-sheng
Related
More- OOpenRouter Image MCPjonathanjudeAnalyzes images through OpenRouter vision models: screenshots, UI debugging and text extraction.AI Models & Services12 Repository stars
- 视视觉看图 MCPgyl1111China调用硅基流动视觉大模型分析图片，让纯文本模型也能看图。AI Models & Services1 Repository stars
- IMCP Image Recognitionmario-andreschakDescribes images using Anthropic and OpenAI vision APIs, with optional Tesseract OCR.AI Models & Services40 Repository stars
- DMCP Docent ServerdongprojectteamGenerates docent-style descriptive captions for an input image using AI.AI Models & Services2 Repository stars
- 作作业批改 MCPpickstar-2002China调用魔搭 Qwen3-VL 多模态模型识别作业图片中的题目与答案，逐题判分并给出解析，支持批量批改。AI Models & Services2 Repository stars
- IMCP Image ValidatorAronMavDescribes and analyzes images with the Qwen3-VL model through the Ollama Cloud API, for checking images produced by other tools.AI Models & Services