Luma MCP
by Bryant927
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TOP_P | No | 核采样阈值 | 0.95 |
| LUMA_DEBUG | No | `1`/`true` 时等同开启 `INCLUDE_META` | |
| MAX_TOKENS | No | 最大生成 token 数(部分模型有硬上限,SiliconFlow DeepSeek-OCR 内部硬性限制在 4096 以内) | 8192 |
| MODEL_NAME | No | 模型名称覆盖(默认自动选择) | |
| MULTI_CROP | No | 大图多裁剪,设为 `false` 关闭 | true |
| CUSTOM_PATH | No | API 路径(custom provider) | /chat/completions |
| TEMPERATURE | No | 采样温度 | 0.7 |
| INCLUDE_META | No | 为 `true` 时在工具结果末尾附加预处理/API 耗时等 meta | false |
| MCP_HTTP_HOST | No | HTTP 模式监听地址(Docker 内需为 `0.0.0.0`) | 0.0.0.0 |
| MCP_HTTP_PORT | No | HTTP 模式监听端口 | 3000 |
| MCP_TRANSPORT | No | 传输方式:`stdio`(默认)或 `http`(Streamable HTTP) | stdio |
| ZHIPU_API_KEY | No | Zhipu 提供商 API Key(MODEL_PROVIDER=zhipu 时使用,默认模型 glm-4.6v) | |
| CUSTOM_API_KEY | No | Custom 提供商 API Key(MODEL_PROVIDER=custom 时使用,任意 OpenAI 兼容端点) | |
| MCP_HTTP_TOKEN | No | HTTP 模式 Bearer token;局域网共享务必设置,否则任何能访问端口的人都能调用 image_understand | |
| MODEL_PROVIDER | No | 模型提供商:`zhipu`、`siliconflow`、`qwen`、`volcengine`、`hunyuan`、`custom` | zhipu |
| CUSTOM_BASE_URL | No | OpenAI 兼容 API 地址(custom provider) | https://api.minimaxi.com/v1 |
| ENABLE_THINKING | No | 思考模式,设为 `false` 关闭 | true |
| HUNYUAN_API_KEY | No | Hunyuan 提供商 API Key(MODEL_PROVIDER=hunyuan 时使用,默认模型 hunyuan-t1-vision-20250916) | |
| CUSTOM_MODEL_NAME | No | 模型名称(custom provider) | MiniMax-M3 |
| CUSTOM_TIMEOUT_MS | No | 请求超时毫秒数(custom provider) | 60000 |
| DASHSCOPE_API_KEY | No | Qwen 提供商 API Key(MODEL_PROVIDER=qwen 时使用,默认模型 qwen3-vl-flash) | |
| BASE_VISION_PROMPT | No | 自定义基础视觉提示词(设为空字符串可关闭) | |
| CUSTOM_AUTH_HEADER | No | 鉴权方式:`bearer` / `x-api-key` / `custom` | bearer |
| VOLCENGINE_API_KEY | No | Volcengine 提供商 API Key(MODEL_PROVIDER=volcengine 时使用,默认模型 doubao-seed-1-6-flash-250828) | |
| SILICONFLOW_API_KEY | No | SiliconFlow 提供商 API Key(MODEL_PROVIDER=siliconflow 时使用,默认模型 deepseek-ai/DeepSeek-OCR) | |
| CUSTOM_THINKING_MODE | No | 思考模式:`disabled` / `openai` / `qwen_extra_body`(custom provider) | disabled |
| MULTI_CROP_MAX_TILES | No | 多裁剪最大图块数(含原图,1–16) | 5 |
| CUSTOM_AUTH_HEADER_VALUE | No | 自定义 Header 模板,例如 `X-API-Key: {{key}}`(`{{key}}` 会被替换为 API Key) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessNo issues