rag-retrieval-mcp
by MaryamZi
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) |
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 | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MaryamZi/rag-retrieval-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server