Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_API_KEYNoOpenAI API key, used with BOSON_SCREEN_CHECK=1 to check unconfirmed sentences against frames on screen (OpenAI's Decisions API). Off by default.
TYPESAFE_API_KEYNoAPI key for TypeSafe's Jev model, used as the checker that verifies every sentence against what was said and finds the moments answering a question.
INCEPTION_API_KEYNoAPI key for Inception's Mercury model, used by default as the writer that produces the summary, English translation and term explanations.
BOSON_SCREEN_CHECKNoSet to 1 to also check against on-screen frames a sentence the words cannot confirm; requires OPENAI_API_KEY. Off by default.
BOSON_WRITER_MODELNoModel name of the OpenAI-compatible writer model.
BOSON_WRITER_API_KEYNoAPI key for the OpenAI-compatible writer model.
BOSON_WRITER_BASE_URLNoBase URL of any OpenAI-compatible model to use as the writer instead of the default Mercury model.

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