Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RAG_DIRNoBase directory for the service; positions corpora.json, .env, corpora and indexes. Defaults to ~/rag-service.~/rag-service
RAG_HOSTNoOverrides the host the MCP server binds to.
RAG_PORTNoOverrides the port the MCP server listens on. Defaults to 8765.8765
RAG_CORPUSYesSelects the corpus to serve. Mandatory; the service refuses to guess.
EMBED_MODELNoEmbedding model name for the embeddings endpoint; may be provided in .env.
RAG_CORPUS_DIRNoOverrides the corpus directory location.
RAG_SERVER_NAMENoOptional MCP server name used for presentation.
RAG_SYSTEM_NOTENoOptional MCP system note used for presentation.
LMSTUDIO_API_KEYNoAPI key for an LM Studio OpenAI-compatible embeddings endpoint; may be provided in .env.
LMSTUDIO_BASE_URLNoBase URL for an LM Studio OpenAI-compatible embeddings endpoint; may be provided in .env.
RAG_EMBED_BACKENDNoOverrides the embeddings backend (e.g., stub for offline demo or LM Studio-compatible endpoint).
RAG_MCP_TRANSPORTNoOverrides the MCP transport (e.g., streamable HTTP).

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