Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MODEL_IDNoAlternate model ID for the selected LLM provider
DEMO_MODENoSeed synthetic demo callsfalse
LLM_MODELNoModel ID for the selected LLM provider
AWS_REGIONNoAWS region for Bedrock if using Amazon Bedrock
DATABASE_URLNoDatabase URL, e.g. postgresql+asyncpg://... or sqlite+aiosqlite://...sqlite+aiosqlite://...
LLM_PROVIDERNoReasoning LLM provider: mock, openai, anthropic, compatible, bedrock, or sarvammock
COACH_MODEL_IDNoCoach model ID override (e.g. sarvam-105b)
MODEL_PROVIDERNoProvider for Bedrock (use bedrock) if using Amazon Bedrock
OPENAI_API_KEYNoVendor key for OpenAI if LLM_PROVIDER=openai
SARVAM_API_KEYNoSarvam AI API key if COACH_MODEL_PROVIDER=sarvam
SARVAM_BASE_URLNoSarvam AI base URLhttps://api.sarvam.ai/v1
SARVAM_MODEL_IDNoSarvam AI model IDsarvam-105b
BEDROCK_MODEL_IDNoBedrock model ID if using Amazon Bedrock
ANTHROPIC_API_KEYNoVendor key for Anthropic if LLM_PROVIDER=anthropic
AWS_ACCESS_KEY_IDNoAWS access key for Bedrock if using Amazon Bedrock
COMPATIBLE_API_KEYNoAPI key for an OpenAI-compatible endpoint if LLM_PROVIDER=compatible
ELEVENLABS_API_KEYNoSpeech provider key for ElevenLabs Scribe v2. Optional - falls back to mock.
COMPATIBLE_BASE_URLNoBase URL for an OpenAI-compatible endpoint if LLM_PROVIDER=compatible
NEXT_PUBLIC_API_URLNoFrontend API base URLhttp://localhost:8000
COACH_MODEL_PROVIDERNoCoach model provider override (e.g. sarvam, mock). Defaults to LLM_PROVIDER.
CONFIDENCE_THRESHOLDNoPipeline confidence threshold knob
ELEVENLABS_STT_MODELNoElevenLabs STT model, e.g. scribe_v2
MAX_RESCORE_ATTEMPTSNoMaximum number of bounded re-score attempts
AWS_SECRET_ACCESS_KEYNoAWS secret access key for Bedrock if using Amazon Bedrock

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