JochenYang/luma-mcp
Multi-Model Visual Understanding MCP Server, GLM-4.6V, DeepSeek-OCR (free), and Qwen3-VL-Flash. Provide visual processing capabilities for AI coding models that do not support image understanding.多模型视觉理解MCP服务器，GLM-4.6V、DeepSeek-OCR（免费）和Qwen3-VL-Flash等。为不支持图片理解的 AI 编码模型提供视觉处理能力。
This tool helps developers integrate advanced image understanding capabilities into their existing AI coding assistants that don't natively support visual input. You provide an image (a local file, URL, or data URI) and a question about it, and the tool returns a detailed analysis. This is ideal for software developers, QA testers, or technical writers who use AI assistants for tasks like debugging code from screenshots, analyzing UI layouts, or extracting text from documentation.
Available on npm.
Use this if your current AI coding assistant lacks the ability to 'see' and interpret images, and you need it to understand screenshots of code, user interfaces, error messages, or dense text documents.
Not ideal if your AI assistant already has strong native visual understanding capabilities, or if you primarily need a standalone image analysis tool for non-development tasks.
Stars
48
Forks
5
Language
TypeScript
License
MIT
Category
Last pushed
Mar 06, 2026
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/JochenYang/luma-mcp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related servers
shinpr/mcp-image
MCP server for AI image generation and editing with automatic prompt optimization and quality...
ifmelate/mcp-image-extractor
MCP server which allow LLM in agent mode to analyze image whenever it needs
joenorton/comfyui-mcp-server
lightweight Python-based MCP (Model Context Protocol) server for local ComfyUI
raveenb/fal-mcp-server
MCP server for Fal.ai - Generate images, videos, music and audio with Claude
glifxyz/glif-mcp-server
Easily run glif.app AI workflows inside your LLM: image generators, memes, selfies, and more....