kasumaputu6633/visbridge-mcp

VisionPower: portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.

Give text-only LLMs vision. A tiny OpenAI-compatible proxy that lets reasoning models (DeepSeek, Qwen, GLM…) see images by querying a separate vision model through tools: look, OCR, scan, crop, compare. No training, no weights.

给 DeepSeek 装上眼睛 — MCP Server + 通义千问VL, 剪贴板图片→视觉模型→文字描述 / Give DeepSeek the ability to see images via clipboard + Qwen-VL

MCP stdio server for image recognition via an existng vision model 一个可以增强claude code/codex/opencode识图能力的MCP

多模型视觉理解 MCP 服务器，为不支持图片理解的 AI 编码模型提供视觉能力：分析截图、报错、UI 与文档，可接入多家主流视觉大模型。Multi-model vision MCP server that adds image understanding to AI coding models without native vision — analyze screenshots, errors, UI and documents via major vision LLM providers.

give non-vision models the ability to see images by routing images to a vision capable model

tiny vision language model

Near-native image understanding for DeepSeek Harness