"author:baker488" matching MCP servers:

Gives AI coding models without native vision the ability to analyze images — screenshots, error messages, UI mockups, and documents — through a single unified image understanding tool. It routes requests to multiple vision model providers (GLM, DeepSeek-OCR, Qwen, Doubao, Hunyuan, or any OpenAI-compatible endpoint) with automatic cropping, compression, OCR-friendly handling, and retries.