Luma MCP
by sahu5182
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 | Set to 1 or true to enable debug metadata, equivalent to INCLUDE_META=true. | |
| MAX_TOKENS | No | Maximum number of generated tokens. | 8192 |
| MODEL_NAME | No | Optional model name override. If omitted, the provider default model is used. | |
| MULTI_CROP | No | Set to false to disable multi-crop processing for large images. | true |
| CUSTOM_PATH | No | Custom provider API path. | /chat/completions |
| TEMPERATURE | No | Sampling temperature. | 0.7 |
| INCLUDE_META | No | Set to true to append preprocessing/API timing metadata to tool results. | false |
| MCP_HTTP_HOST | No | HTTP mode listen address. Docker requires 0.0.0.0. | 0.0.0.0 |
| MCP_HTTP_PORT | No | HTTP mode listen port. | 3000 |
| MCP_TRANSPORT | No | Transport mode: stdio or http. | stdio |
| ZHIPU_API_KEY | No | API key for Zhipu. Used when MODEL_PROVIDER=zhipu, which is the default. | |
| CUSTOM_API_KEY | No | API key for a custom OpenAI-compatible endpoint. Used when MODEL_PROVIDER=custom. | |
| MCP_HTTP_TOKEN | No | Bearer token for HTTP mode. Strongly recommended when sharing over a LAN; if unset, HTTP mode has no authentication. | |
| MODEL_PROVIDER | No | Model provider: zhipu, siliconflow, qwen, volcengine, hunyuan, or custom. | zhipu |
| CUSTOM_BASE_URL | No | Base URL for a custom OpenAI-compatible endpoint. Used when MODEL_PROVIDER=custom. | |
| ENABLE_THINKING | No | Set to false to disable thinking mode. | true |
| HUNYUAN_API_KEY | No | API key for Hunyuan. Used when MODEL_PROVIDER=hunyuan. | |
| CUSTOM_MODEL_NAME | No | Model name for a custom OpenAI-compatible endpoint. Used when MODEL_PROVIDER=custom. | |
| CUSTOM_TIMEOUT_MS | No | Custom provider request timeout in milliseconds. | 60000 |
| DASHSCOPE_API_KEY | No | API key for Qwen/DashScope. Used when MODEL_PROVIDER=qwen. | |
| BASE_VISION_PROMPT | No | Custom base vision prompt. Set to an empty string to disable the built-in default. | |
| CUSTOM_AUTH_HEADER | No | Custom provider auth header mode: bearer, x-api-key, or custom. | bearer |
| VOLCENGINE_API_KEY | No | API key for Volcengine. Used when MODEL_PROVIDER=volcengine. | |
| SILICONFLOW_API_KEY | No | API key for SiliconFlow. Used when MODEL_PROVIDER=siliconflow. | |
| CUSTOM_THINKING_MODE | No | Custom provider thinking mode: disabled, openai, or qwen_extra_body. | disabled |
| MULTI_CROP_MAX_TILES | No | Maximum number of multi-crop tiles, including the original image. Range 1-16. | 5 |
| CUSTOM_AUTH_HEADER_VALUE | No | Custom Header template for the custom provider, e.g. "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