Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoHTTP listener host.127.0.0.1
PORTNoHTTP listener port.3000
NODE_ENVNoSet to production to disable demo defaults and require OWNER_TOKEN and SITTER_TOKEN; also disallows DEMO_CLOCK and VETWISE_DEMO_RESET_MINUTES.
DEMO_CLOCKNoSet to a time such as 21:40 to freeze the demo narrative; refused when NODE_ENV=production.
OWNER_TOKENNoOwner bearer token. Required outside demo mode; defaults to a demo token when VETWISE_DEMO is enabled.
SITTER_TOKENNoSitter bearer token. Required outside demo mode; defaults to a demo token when VETWISE_DEMO is enabled.
VETWISE_DATANoJSON store path; delete to reseed the demo../data/db.json
VETWISE_DEMONoAllow the published demo tokens. Defaults to 1 unless NODE_ENV=production; set to 0 to require real tokens.1
ALLOWED_HOSTSNoRequired behind a tunnel; prevents DNS rebinding.
VETWISE_AGENTNoAgent planner: scripted or bedrock. Defaults to scripted when no AWS credentials are available.scripted
PUBLIC_BASE_URLNoURL the simulator uses to reach its own /mcp endpoint.http://127.0.0.1:3000
BEDROCK_MODEL_IDNoRequired when VETWISE_AGENT=bedrock.amazon.nova-lite-v1:0
CAREGIVER_WEBHOOK_URLNoIf set, caregiver alerts are POSTed and delivery is recorded.
VETWISE_DEMO_RESET_MINUTESNoPublic demos: reseed the household, transcripts and traffic every N minutes; refused when NODE_ENV=production.

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