Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
JEV_PROVIDERNoProvider override: `mock`, `live`, or `openrouter`. Overrides the key-based provider heuristic. With `live` and no resolved credential, startup fails.
TYPESAFE_MODELNoModel id for the TypeSafe route. Defaults to `jev-latest`.
OPENROUTER_MODELNoModel id for the OpenRouter route. Defaults to `jev-latest`; a `typesafe/` prefix requires a versioned id such as `typesafe/jev-1.13`.
TYPESAFE_API_KEYNoSelects the TypeSafe live route when present. If absent and no other provider is selected, the server runs on the offline mock provider.
TYPESAFE_BASE_URLNoAPI root for the TypeSafe route. Defaults to `https://api.typesafe.ai`. Non-HTTPS is refused except on loopback.
OPENROUTER_API_KEYNoSelects the OpenRouter live route when present and no TypeSafe key is set. If absent and no other provider is selected, the server runs on the offline mock provider.
OPENROUTER_BASE_URLNoAPI root for the OpenRouter route. Defaults to `https://openrouter.ai/api`. Non-HTTPS is refused except on loopback.

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