"author:haechanw66" matching MCP servers:

Enables AI assistants that lack native vision to analyze screenshots, error messages, UI layouts, and documents through a single image_understand tool. Routes each request to one of several vision LLM providers (GLM-4.6V, DeepSeek-OCR, Qwen3-VL, Doubao-Seed-1.6, Hunyuan-Vision, or any OpenAI-compatible endpoint) with automatic cropping, compression, and retry handling.