rag-retrieval-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAG_TOP_K | No | Number of results to return | 5 |
| PINECONE_HOST | No | Pinecone index host URL (required when using Pinecone) | |
| OPENAI_API_KEY | No | OpenAI API key (required when using OpenAI) | |
| PGVECTOR_TABLE | No | Table name containing vectors | embeddings |
| PINECONE_API_KEY | No | Pinecone API key (required when using Pinecone) | |
| RAG_VECTOR_STORE | No | Vector store to use | pinecone |
| PINECONE_TEXT_FIELD | No | Metadata field containing text | text |
| PGVECTOR_TEXT_COLUMN | No | Column containing text content | text |
| OPENAI_EMBEDDING_MODEL | No | OpenAI embedding model | text-embedding-3-small |
| RAG_EMBEDDING_PROVIDER | No | Embedding provider to use | openai |
| PGVECTOR_EMBEDDING_COLUMN | No | Column containing embedding vectors | embedding |
| PGVECTOR_CONNECTION_STRING | No | PostgreSQL connection string (required when using pgvector) |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| retrieveC | Search a knowledge base and return relevant content. Args: query: The search query to find relevant content. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no ambiguity. The tool has a clear, single purpose to retrieve content from a knowledge base.
There is only one tool, so naming consistency is not an issue. The name 'retrieve' is a straightforward verb describing the action.
A single tool for a RAG retrieval server feels insufficient. Typically, such a server would require additional tools for knowledge base management, such as adding or deleting documents.
The tool surface is severely incomplete. Only retrieval is supported, with no tools for managing the knowledge base (e.g., create, update, delete documents), leaving agents unable to perform basic lifecycle operations.