by JochenYang · MCP Server · ★ 68
Luma MCP 多模型视觉理解 MCP 服务器,为不支持原生视觉能力的 AI 助手提供统一的图片分析能力。 English | 中文 特性 多模型支持:GLM-4.6V、DeepSeek-OCR、Qwen3-VL-Flash、Doubao-Seed-1.6、Hunyuan-Vision-1.5 单工具设计:统一通过 完成图片理解 面向复杂截图优化:支持大图多裁剪、文本密集场景保真处理 统一预处理链路:本地文件、远程 URL、Data URI 都进入同一套处理流程 适用场景完整:代码截图、UI 截图、报错截图、文档截图、OCR 标准 MCP 协议:可接入 Claude Desktop、Cline、Claude Code 等客户端 内置重试:降低临时网络或模型请求失败带来的影响 快速开始 前置要求 Node.js = 18 任意一个模型提供商的 API Key 安装 也可以在 MCP 配置中直接使用: 配置 Claude Desktop 示例 把 和对应密钥替换为你实际使用的提供商: - - - - - - + + (任意 OpenAI 兼容端点) 可选模型覆盖: Custom Provider(v1.5.0+) 使用任意 OpenAI 兼容端点(OpenAI、OpenRouter、Together AI、Anthropic 代理、本地 vLLM/Ollama 等): bash...
| Stars | 68 |
| Forks | 8 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 68.1610085397925/100 |
| Last Updated | 2026-06-13 |
| Created | 2025-11-11 |
| Platforms | mcp, node |
| Est. Tokens | ~15k |
These tools work well together with luma-mcp for enhanced workflows:
Explore other popular mcp server tools:
luma-mcp is 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. It is categorized as a MCP Server with 68 GitHub stars.
luma-mcp is primarily written in TypeScript. It covers topics such as image-understanding, mcp, mcp-server.
You can find installation instructions and usage details in the luma-mcp GitHub repository at github.com/JochenYang/luma-mcp. The project has 68 stars and 8 forks, indicating an active community.
luma-mcp is released under the MIT license, making it free to use and modify according to the license terms.