Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
WHENSAID_HOMENoDirectory to keep the index in, instead of ~/.whensaid.
WHENSAID_RERANKNoSet to 0 to skip the cross-encoder reranking stage.
WHENSAID_OFFLINENoSet to 1 to forbid any model download (offline mode).
WHENSAID_MIN_RELEVANCENoTunes the relevance threshold for dropping unrelated or borderline results; set to 'off' to disable.
WHENSAID_WHISPER_MODELNoWhisper model to use for transcription, e.g. 'small.en' trades accuracy for speed.
WHENSAID_MIN_CONFIDENCENoMinimum confidence threshold for the transcript check; set to 0 to turn the transcript check off.

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