Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RAG_MODENoSearch mode: `bm25`, `vector`, `hybrid` or `rerank`. Default: `rerank`.
GROQ_API_KEYNoFree-tier Groq API key; a provider without a key is skipped.
RAG_GROQ_MODELNoGroq model name. Default: `openai/gpt-oss-20b`.
RAG_OLLAMA_MODELNoOllama model name. Default: `qwen3.5:9b`.
MCP_ALLOWED_HOSTSNoHost header allowlist for DNS rebinding protection.
RAG_LLM_PROVIDERSNoFallback order of LLM providers; add `ollama` for a local model. Default: `groq,openrouter`.
GENAI_LENS_API_KEYNogenai-lens API key; traces are on when set.
OPENROUTER_API_KEYNoFree-tier OpenRouter API key; a provider without a key is skipped.
GENAI_LENS_ENDPOINTNogenai-lens tracing endpoint; traces are on when set.
RAG_MAX_CONCURRENCYNoNumber of requests doing CPU work at once; the rest wait. Default: `1`.
RAG_MIN_RERANK_SCORENoBelow this score, answer "NÃO ENCONTREI" without calling the LLM. Default: `-3.0`.
RAG_OPENROUTER_MODELNoOpenRouter model name. Default: `google/gemma-4-26b-a4b-it:free`.

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