Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoPort used when running the container.
NOVA_LLMNoAgent brain: `auto` (Bedrock, then Ollama, then rules), `bedrock`, `ollama` or `rules`.auto
NOVA_DEMONoDemo-only routes (`/demo/reset`, `/demo/clock`); set `0` in production.1
AWS_REGIONNoRegion for Amazon Bedrock and Polly (standard AWS credential chain).us-east-1
NOVA_CLOCKNoStart the household clock at a given time, e.g. `08:20`.
NOVA_MODEL_IDNoPin a specific Amazon Nova model or inference profile.
RING_CLIENT_IDNoProduction Ring account linking client ID.
SIMULATOR_PORTNoSimulator port.8080
NOVA_PUBLIC_URLNoPublic base URL (OAuth metadata and allowed hosts).
RING_ACCESS_TOKENNoRing Developer Playground token (about 30 minutes).
RING_POLL_SECONDSNoEvent-history backfill interval when Ring is linked.300
RING_CLIENT_SECRETNoProduction Ring account linking client secret.
RING_REFRESH_TOKENNoProduction Ring account linking refresh token.
NOVA_RING_SIGNING_KEYNoKey Ring signs webhooks with.
NOVA_LLM_RETRY_SECONDSNoHow often an unavailable Bedrock is retried in the background.600

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