Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
JEV_HOSTNoHTTP bind address. Defaults to '0.0.0.0' in Docker.127.0.0.1
JEV_PORTNoHTTP port.8000
JEV_API_BASENoAPI base URL (useful for testing/mocking).https://api.typesafe.ai
JEV_HTTP_PATHNoStreamable HTTP endpoint path./mcp
JEV_TRANSPORTNoMCP transport. Defaults to 'stdio', but 'streamable-http' is used in Docker.stdio
JEV_MAX_RETRIESNoNumber of retries for HTTP 429/529 responses.3
JEV_TIMEOUT_SECNoPer-request HTTP timeout in seconds.30
TYPESAFE_API_KEYYesBearer token from TypeSafe console. Required to authenticate with the TypeSafe API.
JEV_DEFAULT_MODELNoDefault model for tool calls.jev-latest
JEV_STATELESS_HTTPNoWhether to use stateless HTTP sessions.true

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