Luma MCP
by Khalidw48
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 mode (equivalent to INCLUDE_META). | |
| MAX_TOKENS | No | Maximum number of tokens to generate. Note: for SiliconFlow (DeepSeek-OCR), it is hard-capped at 4096. | 8192 |
| MODEL_NAME | No | Override the model name. If not set, a default model for the provider is used. | |
| MULTI_CROP | No | Set to 'false' to disable multi-crop for large images. | true |
| CUSTOM_PATH | No | API path for custom provider. | /chat/completions |
| TEMPERATURE | No | Sampling temperature. | 0.7 |
| INCLUDE_META | No | Set to 'true' to append preprocessing/API timing meta to tool results. | false |
| MCP_HTTP_HOST | No | HTTP mode listen address (use 0.0.0.0 inside Docker). | 0.0.0.0 |
| MCP_HTTP_PORT | No | HTTP mode listen port. | 3000 |
| MCP_TRANSPORT | No | Transport method: 'stdio' (default) or 'http' (Streamable HTTP). | stdio |
| ZHIPU_API_KEY | No | API key for Zhipu provider. | |
| CUSTOM_API_KEY | No | API key for custom OpenAI-compatible endpoint. | |
| MCP_HTTP_TOKEN | No | HTTP mode Bearer token. Strongly recommended when using HTTP mode. | |
| MODEL_PROVIDER | No | Model provider: 'zhipu', 'siliconflow', 'qwen', 'volcengine', 'hunyuan', or 'custom'. | zhipu |
| CUSTOM_BASE_URL | No | Base URL for custom OpenAI-compatible endpoint (e.g., https://your-endpoint.com/v1). | |
| ENABLE_THINKING | No | Set to 'false' to disable thinking mode. | true |
| HUNYUAN_API_KEY | No | API key for Hunyuan provider. | |
| CUSTOM_MODEL_NAME | No | Model name for custom provider. | |
| CUSTOM_TIMEOUT_MS | No | Timeout in milliseconds for custom provider. | 60000 |
| DASHSCOPE_API_KEY | No | API key for Qwen provider (DashScope). | |
| BASE_VISION_PROMPT | No | Custom base vision prompt. Set to empty string to disable. | |
| CUSTOM_AUTH_HEADER | No | Authentication header type: 'bearer', 'x-api-key', or 'custom'. | bearer |
| VOLCENGINE_API_KEY | No | API key for Volcengine provider. | |
| SILICONFLOW_API_KEY | No | API key for SiliconFlow provider. | |
| CUSTOM_THINKING_MODE | No | Thinking mode for custom provider: 'disabled', 'openai', or 'qwen_extra_body'. | disabled |
| MULTI_CROP_MAX_TILES | No | Maximum number of tiles for multi-crop (including original image, 1-16). | 5 |
| CUSTOM_AUTH_HEADER_VALUE | No | Custom auth header template, e.g., 'X-API-Key: {{key}}'. {{key}} is replaced by 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