Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
FRANKENFISH_SOURCENoSet to `goofish` to enable live mode, querying goofish-cli on the seller's own account (at most 3 queries per minute, results cached for 1 hour). Requires goofish-cli to be installed and authenticated via `goofish auth login --qr`. If unset, goofish-cli is missing, or not logged in, FrankenFish falls back to bundled demo data automatically.
FRANKENFISH_LLM_KEYNoAPI key for the OpenAI-compatible LLM (e.g. sk-...). Optional; when LLM settings are unset, replies fall back to rule-based drafts.
FRANKENFISH_LLM_MODELNoModel name to use, e.g. gpt-4o-mini (any OpenAI-compatible model). Optional; when LLM settings are unset, replies fall back to rule-based drafts.
FRANKENFISH_LLM_BASE_URLNoBase URL of an OpenAI-compatible LLM API (e.g. https://api.openai.com/v1). Optional; when LLM settings are unset, replies fall back to rule-based drafts.

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