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。
Implements an MCP server with pluggable vision model backends (Zhipu, SiliconFlow, Qwen, Volcengine, Hunyuan), automatically handling image preprocessing including compression, multi-crop tiling for dense text scenes, and format normalization across local files, URLs, and Data URIs. Exposes a single `image_understand` tool that integrates with Claude Desktop, Cline, and Claude Code, with configurable thinking mode and adaptive cropping strategies optimized for code/UI/OCR screenshots.
Available on npm.
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
raveenb/fal-mcp-server
MCP server for Fal.ai - Generate images, videos, music and audio with Claude
sunriseapps/imagesorcery-mcp
An MCP server providing tools for image processing operations
shinpr/mcp-image
MCP server for AI image generation and editing with automatic prompt optimization and quality...
glifxyz/glif-mcp-server
Easily run glif.app AI workflows inside your LLM: image generators, memes, selfies, and more....
joenorton/comfyui-mcp-server
lightweight Python-based MCP (Model Context Protocol) server for local ComfyUI