Skip to main content
Glama
fayna-digital

fayna-rag-mcp

Official

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TOP_KNoNumber of chunks returned by retrieval.5
MCP_HOSTNoHost to bind when MCP_TRANSPORT=http.0.0.0.0
MCP_PORTNoPort to bind when MCP_TRANSPORT=http.8765
CHUNK_SIZENoChunk size in tokens (tiktoken).700
OLLAMA_URLNoOllama API endpoint.http://localhost:11434/api/generate
OLLAMA_MODELNoOllama model used for RAG answers.qwen2.5:7b
CHUNK_OVERLAPNoChunk overlap in tokens.100
DOCUMENTS_DIRNoRoot directory of the knowledge base documents../docs
MCP_TRANSPORTNoMCP transport: stdio or http.stdio
EMBEDDING_MODELNoEmbedding model used for vector search.paraphrase-multilingual-mpnet-base-v2

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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources