# luma-mcp

> luma-mcp — jochenyang-luma-mcp. Use this tool when you need to enhance AI coding models with visual understanding capabilities, solving problems such as image recognition and processing for models that lack native support. It provides a multi-model server with various visual processing capabilities, including OCR and visual-language understanding, and accepts image inputs to generate actionable outputs. Ideal for use cases where AI models require image analysis and interpretation to inform coding decisions.

Canonical page: https://skillsregistry.net/skills/jochenyang-luma-mcp  
JSON: https://api.skillsregistry.net/v1/skills/jochenyang-luma-mcp

## Description

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.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** media
- **Updated:** 2026-09-24

## Source

- **Source listing:** [GitHub](https://github.com/JochenYang/luma-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "jochenyang-luma-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jochenyang-luma-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jochenyang-luma-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt