"author:Jsliu28" matching MCP servers:

Enables text-only models to understand images by intercepting pasted images, saving them locally, and using a vision MCP server to analyze them with multimodal backends like Qwen-VL, Doubao, or GLM-4V.

MCP server that gives non-image-capable models like DeepSeek the ability to generate images using backends such as Qwen-Image, Seedream, and CogView, saving them locally and returning file paths instead of base64 data.