Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Enable debug timing logs ('true' or '1'). | false |
| HTTP_PORT | No | Port for HTTP transport. | 3000 |
| QDRANT_URL | No | Qdrant server URL. | http://localhost:6333 |
| COHERE_API_KEY | No | API key for Cohere. | |
| OPENAI_API_KEY | No | API key for OpenAI. | |
| QDRANT_API_KEY | No | API key for Qdrant authentication. | |
| TRANSPORT_MODE | No | Transport mode: 'stdio' or 'http'. | stdio |
| VOYAGE_API_KEY | No | API key for Voyage AI. | |
| CODE_BATCH_SIZE | No | Number of chunks to embed in one batch. | 100 |
| CODE_CHUNK_SIZE | No | Maximum chunk size in characters for code indexing. | 2500 |
| CODE_ENABLE_AST | No | Enable AST-aware chunking using tree-sitter. | true |
| EMBEDDING_MODEL | No | The model name for embeddings. Provider-specific defaults apply if omitted. | |
| DELETE_BATCH_SIZE | No | Paths per delete batch. | 500 |
| CODE_CHUNK_OVERLAP | No | Overlap between chunks in characters. | 300 |
| CODE_CUSTOM_IGNORE | No | Additional ignore patterns (comma-separated). | |
| CODE_DEFAULT_LIMIT | No | Default search result limit for code search. | 5 |
| DELETE_CONCURRENCY | No | Parallel delete requests. | 8 |
| EMBEDDING_BASE_URL | No | Custom API URL for the embedding provider. | |
| EMBEDDING_PROVIDER | No | The embedding provider to use: 'ollama', 'openai', 'cohere', or 'voyage'. | ollama |
| MAX_IO_CONCURRENCY | No | Maximum parallel file I/O operations during cache sync. | 50 |
| EMBEDDING_DIMENSION | No | Vector dimensions (auto-detected from model if possible). | |
| PROMPTS_CONFIG_FILE | No | Path to prompts configuration JSON. | prompts.json |
| EMBEDDING_BATCH_SIZE | No | Number of texts per embedding request. | 64 |
| EMBEDDING_CONCURRENCY | No | Parallel embedding requests (useful for multiple GPUs). | 1 |
| EMBEDDING_RETRY_DELAY | No | Initial retry delay in milliseconds. | 1000 |
| QDRANT_BATCH_ORDERING | No | Ordering mode: 'weak', 'medium', or 'strong'. | weak |
| CODE_CUSTOM_EXTENSIONS | No | Additional file extensions (comma-separated) for indexing. | |
| HTTP_REQUEST_TIMEOUT_MS | No | Request timeout for HTTP transport in milliseconds. | 300000 |
| CODE_ENABLE_GIT_METADATA | No | Enrich chunks with git blame information (author, dates, tasks). | false |
| EMBEDDING_RETRY_ATTEMPTS | No | Number of retry attempts for embedding requests. | 3 |
| QDRANT_FLUSH_INTERVAL_MS | No | Auto-flush buffer interval for Qdrant (0 to disable). | 500 |
| EMBEDDING_MAX_REQUESTS_PER_MINUTE | No | Rate limit for embedding requests. |
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 | |