Luma MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TOP_P | No | Nucleus sampling threshold | 0.95 |
| LUMA_DEBUG | No | `1`/`true` is equivalent to enabling `INCLUDE_META` | 关闭 |
| MAX_TOKENS | No | Maximum number of generated tokens. For SiliconFlow (DeepSeek-OCR) this is hard-capped at 4096 internally | 8192 |
| MODEL_NAME | No | Model name override (auto-selected per provider by default). E.g. `doubao-seed-1-6-vision-250815` (Volcengine) or `hy-vision-2.0-instruct` (Hunyuan, Tencent Cloud TokenHub) | 自动选择 |
| MULTI_CROP | No | Multi-crop for large images; set to `false` to disable | true |
| CUSTOM_PATH | No | Custom provider API path | /chat/completions |
| TEMPERATURE | No | Sampling temperature | 0.7 |
| INCLUDE_META | No | When `true`, appends preprocessing/API timing meta to the end of the tool result | false |
| MCP_HTTP_HOST | No | HTTP mode listen address (must be `0.0.0.0` inside Docker) | 0.0.0.0 |
| MCP_HTTP_PORT | No | HTTP mode listen port | 3000 |
| MCP_TRANSPORT | No | Transport mode: `stdio` (default) or `http` (Streamable HTTP) | stdio |
| ZHIPU_API_KEY | No | API key for the Zhipu provider (default model `glm-4.6v`) | |
| CUSTOM_API_KEY | No | API key for any OpenAI-compatible endpoint (used with the `custom` provider) | |
| MCP_HTTP_TOKEN | No | Bearer token for HTTP mode (no auth when empty); strongly recommended if sharing on a LAN, otherwise anyone who can reach the port can call `image_understand` and consume your model API quota | |
| MODEL_PROVIDER | No | Model provider: `zhipu`, `siliconflow`, `qwen`, `volcengine`, `hunyuan`, or `custom` | zhipu |
| CUSTOM_BASE_URL | No | OpenAI-compatible API base URL (custom provider) | https://api.minimaxi.com/v1 |
| ENABLE_THINKING | No | Thinking mode; set to `false` to disable | true |
| HUNYUAN_API_KEY | No | API key for the Hunyuan provider (default model `hunyuan-t1-vision-20250916`) | |
| CUSTOM_MODEL_NAME | No | Model name (custom provider) | MiniMax-M3 |
| CUSTOM_TIMEOUT_MS | No | Custom provider timeout in milliseconds | 60000 |
| DASHSCOPE_API_KEY | No | API key for the Qwen provider (default model `qwen3-vl-flash`) | |
| BASE_VISION_PROMPT | No | Custom base vision prompt (set to an empty string to disable) | 内置默认值 |
| CUSTOM_AUTH_HEADER | No | Custom provider auth header style: `bearer` / `x-api-key` / `custom` | bearer |
| VOLCENGINE_API_KEY | No | API key for the Volcengine provider (default model `doubao-seed-1-6-flash-250828`) | |
| SILICONFLOW_API_KEY | No | API key for the SiliconFlow provider (default model `deepseek-ai/DeepSeek-OCR`) | |
| CUSTOM_THINKING_MODE | No | Custom provider thinking mode: `disabled` / `openai` / `qwen_extra_body` | disabled |
| MULTI_CROP_MAX_TILES | No | Maximum number of tiles for multi-crop (including the original image, 1–16) | 5 |
| CUSTOM_AUTH_HEADER_VALUE | No | Custom Header template (`{{key}}` is replaced with the API key) | 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
ResponsivenessResponsive