Luma MCP
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,默认关闭 | |
| MAX_TOKENS | No | 最大生成 token 数(部分模型有硬上限,SiliconFlow 的 DeepSeek-OCR 会被硬性限制在 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 | Custom provider 的 API 路径 | /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 提供商的 API Key(MODEL_PROVIDER=zhipu,默认模型 glm-4.6v) | |
| CUSTOM_API_KEY | No | Custom provider 的 API Key(MODEL_PROVIDER=custom,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,默认为空(不鉴权) | |
| MODEL_PROVIDER | No | 模型提供商:zhipu、siliconflow、qwen、volcengine、hunyuan、custom | zhipu |
| CUSTOM_BASE_URL | No | Custom provider 的 OpenAI 兼容 API 地址(如 https://your-endpoint.com/v1) | https://api.minimaxi.com/v1 |
| ENABLE_THINKING | No | 思考模式,设为 false 关闭 | true |
| HUNYUAN_API_KEY | No | Hunyuan 提供商的 API Key(MODEL_PROVIDER=hunyuan,默认模型 hunyuan-t1-vision-20250916) | |
| CUSTOM_MODEL_NAME | No | Custom provider 的模型名称 | MiniMax-M3 |
| CUSTOM_TIMEOUT_MS | No | Custom provider 超时毫秒 | 60000 |
| DASHSCOPE_API_KEY | No | Qwen 提供商的 API Key(MODEL_PROVIDER=qwen,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),默认使用内置默认值 | |
| CUSTOM_AUTH_HEADER | No | Custom provider 鉴权方式:bearer / x-api-key / custom | bearer |
| VOLCENGINE_API_KEY | No | Volcengine 提供商的 API Key(MODEL_PROVIDER=volcengine,默认模型 doubao-seed-1-6-flash-250828) | |
| SILICONFLOW_API_KEY | No | SiliconFlow 提供商的 API Key(MODEL_PROVIDER=siliconflow,默认模型 deepseek-ai/DeepSeek-OCR) | |
| CUSTOM_THINKING_MODE | No | Custom provider 思考模式:disabled / openai / qwen_extra_body | 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({{key}} 会被替换为 API Key),例如 "X-API-Key: {{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