Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoPort the Express server listens on (default 3000). Serves the web simulator at / and the MCP endpoint at /mcp.
AWS_REGIONNoThe AWS region used for Amazon Bedrock (ConverseCommand) speech parsing and message drafting.
UDHAAR_API_KEYNoBearer token required for /mcp and /api/* (constant-time comparison). When unset, auth is open — set it before exposing the server publicly. /health always stays open.
BEDROCK_MODEL_IDNoThe Bedrock model ID or inference profile ID (e.g. us.anthropic.claude-..., eu.anthropic.claude-..., global.anthropic.claude-...) used for Bedrock calls. Many current Claude models require an inference profile ID rather than the raw foundation-model ID.
UDHAAR_DATA_FILENoPath to the JSON-file ledger store used to persist the credit ledger.
UDHAAR_DISABLE_BEDROCKNoSet to 1 to disable Bedrock; speech parsing and reminder drafting fall back to deterministic regex/template logic, allowing the server to run with no AWS credentials at all.

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