doc-rag-mcp
by theniitettey
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAG_PORT | No | Port for HTTP server. Default 8743. | |
| RAG_DOCS_DIR | No | Path to the docs folder for reindexing. Default is ./docs. | |
| RAG_AUTH_TOKEN | No | Bearer token for HTTP authentication. Required when running with --transport http. | |
| RAG_COLLECTION | Yes | The collection name to query. Should match the collection used during ingestion. | |
| VOYAGE_API_KEY | Yes | Your Voyage AI API key. Required for generating embeddings. | |
| RAG_EMBED_MODEL | No | Embedding model to use for queries. Must match the model used for ingestion. Default is voyage-4-large. | |
| RAG_DATABASE_URL | Yes | PostgreSQL connection URL, e.g., postgresql://raguser:yourpassword@localhost:5433/ragdb | |
| RAG_RERANK_MODEL | No | Optional rerank model (e.g., rerank-2.5). If set, enables reranking of search results. | |
| RAG_CACHE_MAX_SIZE | No | Maximum number of query results to cache. Default 256. | |
| RAG_CACHE_TTL_SECONDS | No | Cache TTL in seconds. Default 600. |
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
ActivityMaintained
ResponsivenessNo issues