Skip to main content
Glama
Back2Base
by Back2Base

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MODEL_GUIDENoIngest configuration model used to generate the learned prose guide.@cf/openai/gpt-oss-120b
ALLOWED_SUBSNoSecret fixed Auth0 subject allowlist. Access requires a fixed subject in this secret, checked again on each API request. Filled by `pnpm auth:configure` with the verified identities for `TONES_OWNER_EMAIL`.
AUTH0_DOMAINYesYour Auth0 domain. Tones delegates identity sign-in to your Auth0 tenant.
AI_GATEWAY_IDNoThe AI Gateway ID used for guide calls (`style-mcp`). AI Gateway must have logging and caching enabled.
INGEST_ORIGINNoThe origin of the ingestion Worker, set in .env during provisioning.
PUBLIC_ORIGINNoThe public origin of your deployment. The MCP endpoint is `<PUBLIC_ORIGIN>/mcp`. Set in workers/mcp/wrangler.jsonc (and the custom-domain `routes` entry, if you use one).
TONES_OWNER_EMAILYesYour owner email. Used by `pnpm auth:configure` to create the dedicated Auth0 `Tones` application and to fill `ALLOWED_SUBS` with the verified identities for this email.
CLOUDFLARE_ACCOUNT_IDNoCloudflare account ID used by `pnpm provision` to replace placeholder resource IDs (set this or sign in with Wrangler to choose the account).

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