Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_URL | No | The URL of the LLM API endpoint (e.g., 'http://host.docker.internal:12434/v1' for local, 'https://openrouter.ai/api/v1' for OpenRouter) | |
| LLM_MODEL | No | The LLM model to use (e.g., 'llama3.3:8b' for local, 'deepseek/deepseek-chat' for OpenRouter) | |
| LLM_API_KEY | No | The API key for the LLM provider (use 'not-needed' for local models, or your actual API key for OpenRouter) | |
| RELATIONSHIP_PROVIDER | No | The LLM provider to use for relationship extraction (e.g., 'openai' for local Docker, 'openrouter' for cloud) |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search | Search the GraphRAG knowledge base with THREE distinct modes: CRITICAL: For ticker symbols (ASTS, RKLB, NBIS) or acronyms, ALWAYS use 'keyword_lookup' FIRST. Semantic search (entity_connections/thematic_overview) can MISS exact ticker matches. Workflow:
Mode Selection Guide:
|
| explore_entity_graph | Traverse the knowledge graph starting from a specific entity. Returns the entity, its direct connections (other entities), and the relationships between them. Use this to build reasoning chains or verify facts about a known entity. |
| get_corpus_stats | Get statistics about the indexed knowledge base. Returns counts of documents, chunks, entities, and relationships. Use for corpus health checks or to understand the scale of available data. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |