Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TRANSPORT | No | Transport mode: stdio or http | |
| DIMENSIONS | No | Embedding dimensions | 1024 |
| CONFIG_PATH | No | Path to MCP configuration file (mcp-servers.json) | |
| OPENAI_API_KEY | Yes | OpenAI API key for embeddings and descriptions | |
| DESCRIBE_IMAGES | No | Use vision to describe images | true |
| QDRANT_DATA_PATH | Yes | Path to local directory for embedded Qdrant vector database (no separate server needed) | |
| MAX_RESULT_TOKENS | No | Chunk threshold for large results | 5000 |
| VISION_MODEL_NAME | No | Model for describing images | gpt-4.1-mini |
| EMBEDDING_MODEL_NAME | No | OpenAI embedding model | text-embedding-3-small |
| DESCRIPTOR_MODEL_NAME | No | Model for generating tool descriptions | gpt-4.1-mini |
| TOOL_OFFLOADED_DATA_PATH | Yes | Path for storing offloaded content (large results, images) |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |