Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOMEPULSE_DATANoLocation of the HomePulse data file (home.json).
HOMEPULSE_PORTNoPort for the HomePulse server. If the usual port is busy, HomePulse uses the next free one and prints the address.
HOMEPULSE_MCP_TOKENNoBearer token required in the Authorization header for MCP requests. Defaults to the public demo token; set your own to change it.
HOMEPULSE_LATENCY_MSNoSimulated network delay per attempt on the sample home, in milliseconds. Default is 150.
HOMEPULSE_ALLOWED_HOSTSNoHost names allowed when exposing HomePulse through a tunnel.
HOMEPULSE_WATCH_SECONDSNoInterval in seconds for background live-watch checks. Set to 0 to turn the live watch off.
HOMEPULSE_WATCH_CONFIRMSNoNumber of consecutive missed checks required before an outage is confirmed.

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