Luma MCP
by sChauhan9915
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TOP_P | No | Nucleus sampling threshold. Default: 0.95. | |
| LUMA_DEBUG | No | When set to 1 or true, equivalent to enabling INCLUDE_META. | |
| MAX_TOKENS | No | Maximum generated tokens. Default: 8192. SiliconFlow DeepSeek-OCR is internally capped at 4096. | |
| MODEL_NAME | No | Optional model name override. | |
| MULTI_CROP | No | Enable multi-crop for large images. Set to false to disable. Default: true. | |
| CUSTOM_PATH | No | Custom provider API path. Default: /chat/completions. | |
| TEMPERATURE | No | Sampling temperature. Default: 0.7. | |
| INCLUDE_META | No | When true, append preprocessing/API timing metadata to tool results. Default: false. | |
| MCP_HTTP_HOST | No | HTTP mode listen address. Default: 0.0.0.0. Docker requires 0.0.0.0. | |
| MCP_HTTP_PORT | No | HTTP mode listen port. Default: 3000. | |
| MCP_TRANSPORT | No | Transport mode: stdio or http. Default: stdio. | |
| ZHIPU_API_KEY | No | API key for the Zhipu provider. | |
| CUSTOM_API_KEY | No | API key for the custom OpenAI-compatible provider. | |
| MCP_HTTP_TOKEN | No | Bearer token for HTTP mode. Strongly recommended for LAN sharing. | |
| MODEL_PROVIDER | No | Model provider. One of: zhipu, siliconflow, qwen, volcengine, hunyuan, custom. Default: zhipu. | |
| CUSTOM_BASE_URL | No | OpenAI-compatible API base URL for the custom provider. | |
| ENABLE_THINKING | No | Enable thinking mode. Set to false to disable. Default: true. | |
| HUNYUAN_API_KEY | No | API key for the Hunyuan provider. | |
| CUSTOM_MODEL_NAME | No | Model name for the custom provider. | |
| CUSTOM_TIMEOUT_MS | No | Custom provider request timeout in milliseconds. Default: 60000. | |
| DASHSCOPE_API_KEY | No | API key for the Qwen/DashScope provider. | |
| BASE_VISION_PROMPT | No | Custom base vision prompt. Set to an empty string to disable. | |
| CUSTOM_AUTH_HEADER | No | Custom provider auth header mode: bearer, x-api-key, or custom. Default: bearer. | |
| VOLCENGINE_API_KEY | No | API key for the Volcengine provider. | |
| SILICONFLOW_API_KEY | No | API key for the SiliconFlow provider. | |
| CUSTOM_THINKING_MODE | No | Custom provider thinking mode: disabled, openai, or qwen_extra_body. Default: disabled. | |
| MULTI_CROP_MAX_TILES | No | Maximum number of crop tiles including the original image, from 1 to 16. Default: 5. | |
| CUSTOM_AUTH_HEADER_VALUE | No | Custom auth header template, e.g. "X-API-Key: {{key}}". {{key}} is replaced with the 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