# Luma

> Multi-model vision understanding MCP server. Supports GLM-4.6V (Zhipu), DeepSeek-OCR (SiliconFlow - Free), Qwen3-VL-Flash (Aliyun), and Doubao-Seed-1.6 (Volcengine)

## Facts
- Page: https://tashan.sh/capability/pkg-luma-mcp
- tashan id: pkg:luma-mcp
- Source: https://github.com/JochenYang/luma-mcp
- npm: https://www.npmjs.com/package/luma-mcp
- Type: npm
- Category: ai
- tashan score: 71.0 / 100
- Adoption: 49.0
- Upkeep: 73.0
- Freshness: 99.0
- Evidence coverage: 100% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- npm downloads: 3,039/week
- Official: no

## Install

```sh
claude mcp add luma -- npx -y luma-mcp
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-08 by tashan (https://tashan.sh) from public evidence. Scorer s5.