58
/ 100
1 month ago
github_topic

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。

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
⚠️
Known vulnerabilities in dependencies: 9 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 6 credentials: CUSTOM_API_KEY, DASHSCOPE_API_KEY, HUNYUAN_API_KEY, SILICONFLOW_API_KEY, VOLCENGINE_API_KEY, ZHIPU_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// known CVEs in dependencies9 high2 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.25.4GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

highaxios@1.15.1GHSA-35jp-ww65-95wh

axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`

highaxios@1.15.1GHSA-3g43-6gmg-66jw

axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge

highaxios@1.15.1GHSA-777c-7fjr-54vf

Allocation of Resources Without Limits or Throttling in Axios

highaxios@1.15.1GHSA-hfxv-24rg-xrqf

Axios: Regular Expression Denial of Service (ReDoS) via Cookie Name Injection

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
configBASE_VISION_PROMPT内置默认值 自定义基础视觉提示词
🔐 secretCUSTOM_API_KEYcustom -> + CUSTOM_BASE_URL + CUSTOM_MODEL_NAME(任意 OpenAI 兼容端点)
configCUSTOM_AUTH_HEADERbearer — bearer / x-api-key / custom
configCUSTOM_AUTH_HEADER_VALUE"X-API-Key: {{key}}" — 自定义 Header 模板
configCUSTOM_BASE_URLcustom -> CUSTOM_API_KEY + + CUSTOM_MODEL_NAME(任意 OpenAI 兼容端点)
configCUSTOM_MODEL_NAMEcustom -> CUSTOM_API_KEY + CUSTOM_BASE_URL + (任意 OpenAI 兼容端点)
configCUSTOM_PATH/chat/completions — API 路径
configCUSTOM_THINKING_MODEdisabled — disabled / openai / qwen_extra_body
configCUSTOM_TIMEOUT_MS60000 — 超时毫秒
🔐 secretDASHSCOPE_API_KEYclaude mcp add -s user luma-mcp --env MODEL_PROVIDER=qwen --env =your-api-key -- npx -y luma-mcp
configENABLE_THINKING
🔐 secretHUNYUAN_API_KEYhunyuan ->
configMAX_TOKENS8192 最大生成 token 数(部分模型有硬上限,详见下方说明)
configMODEL_NAMEdoubao-seed-1-6-flash-250828
configMODEL_PROVIDER"": "zhipu",
configMULTI_CROP
configMULTI_CROP_MAX_TILES
🔐 secretSILICONFLOW_API_KEYsiliconflow ->
configTOP_P
🔐 secretVOLCENGINE_API_KEYvolcengine ->
🔐 secretZHIPU_API_KEY"": "your-api-key"
// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/jochenyang-luma-mcp-guaqp3)](https://m8ven.ai/mcp/jochenyang-luma-mcp-guaqp3)
commit: 9831a4861960cabeb1f10d834b7e081aa557eda5
code hash: 376a826dc6b940eaaf33178511693d959725f8adb15aaa29fbcb5c8fe2b246db
verified: 6/15/2026, 1:35:57 PM
view raw JSON →