Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoOptional. Host to bind for the HTTP transports; use `127.0.0.1` outside a container. There is no authentication on the HTTP transports, so run the server on a private docker network or on localhost and do not expose it.0.0.0.0
PORTNoOptional. Port to listen on for the HTTP transports.8788
TRANSPORTNoOptional. Transport to use: `http` (streamable HTTP + SSE) or `stdio` (for Claude Desktop and other launchers, where stdout is the protocol and logs go to stderr).http
POSITIONGUARD_API_KEYYesRequired. Your PositionGuard API key; it must start with `pg_live_` or the server refuses to start. Create the key in the developer portal with type **Assistant** (an Integration key works mechanically but bypasses the member consent gate).
POSITIONGUARD_API_BASENoOptional. Base URL of the PositionGuard REST API.https://api.positionguardai.com/api/v1

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