knowledge-server
by bwarzecha
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAX_TOKENS | No | Maximum tokens per chunk | 8192 |
| API_INDEX_PATH | No | Path to API index file | ./data/api_index.json |
| EMBEDDING_MODEL | No | Sentence-transformers model | dunzhang/stella_en_1.5B_v5 |
| MCP_SERVER_HOST | No | MCP server host | localhost |
| MCP_SERVER_NAME | No | MCP server display name | Knowledge Server |
| MCP_SERVER_PORT | No | MCP server port | 8000 |
| EMBEDDING_DEVICE | No | Device for embeddings (mps, cpu, cuda, auto) | mps |
| VECTOR_STORE_DIR | No | Vector store persistence directory | ./data/vectorstore |
| OPENAPI_SPECS_DIR | Yes | Directory containing OpenAPI specs | |
| RETRIEVAL_MAX_DEPTH | No | Max reference expansion depth | 3 |
| RETRIEVAL_TIMEOUT_MS | No | Retrieval timeout in milliseconds | 5000 |
| VECTOR_STORE_COLLECTION | No | Vector store collection name | knowledge_base |
| RETRIEVAL_MAX_TOTAL_CHUNKS | No | Max total chunks retrieved | 15 |
| RETRIEVAL_MAX_PRIMARY_RESULTS | No | Max primary search results | 5 |
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
ActivityInactive
ResponsivenessNo issues