Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
JEV_API_KEYNoRequired for observe with an instruction, act without candidateId, and extract. TYPESAFE_API_KEY is used when it is not set or empty.
CUA_JEV_MODELNoThe Jev model (default `jev-latest`).jev-latest
CUA_DRIVER_BINNoPath to cua-driver (default `~/.local/bin/cua-driver`; a leading `~` is expanded).~/.local/bin/cua-driver
JEV_READ_TIMEOUTNoSeconds to wait for Jev's answer to one request (default 120).120
TYPESAFE_API_KEYNoFallback for JEV_API_KEY. Used when JEV_API_KEY is not set or empty.
CUA_JEV_LOG_LEVELNoLevel of the server's log on stderr (default `WARNING`).WARNING
TYPESAFE_BASE_URLNoThe Jev endpoint (default `https://api.typesafe.ai`).https://api.typesafe.ai
CUA_DRIVER_TIMEOUTNoSeconds to wait for cua-driver to start, and for its answer to each call (default 120).120
JEV_CONNECT_TIMEOUTNoSeconds to wait for a connection to Jev (default 10).10
CUA_JEV_EFFECT_RETAKESNoFresh snapshots taken to see an effect (default 5).5

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