Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoServer port (default: 8000; Cloud Run injects 8080)8000
LOG_LEVELNoDEBUG, INFO (default), WARNING, or ERRORINFO
LOG_FORMATNojson or text. Defaults to json on Cloud Run (detected via K_SERVICE), text elsewhere.
GARMIN_EMAILNoYour Garmin Connect email
READYZ_TOKENNoRequired. Bearer token guarding /readyz, checked independently of OAuth so it still answers when the OAuth layer itself is broken.
GARMIN_PASSWORDNoOptional. Only used to re-authenticate if the stored tokens expire.
PUBLIC_BASE_URLNoRequired. The service's externally reachable URL, e.g. https://garmlink-moz6szqd6q-uc.a.run.app. OAuth callback URLs (/auth/callback) are derived from it.
GITHUB_CLIENT_IDNoRequired (unless ALLOW_UNAUTHENTICATED=1). Client ID of the GitHub OAuth App backing the claude.ai connector.
GARMIN_TOKENS_JSONNoBase64-encoded token file (from garmlink-auth). A seed, not the live credential: Garmin rotates the refresh token, and rotations are persisted to Firestore, which then takes precedence. Re-seed only to bootstrap a new deployment or recover a stored blob that has gone bad.
GITHUB_ALLOWED_USERSNoRequired. Comma-separated GitHub logins allowed to use the server — the only access control once OAuth is on, so it fails closed: a blank value or a list naming nobody (e.g. ,,) both abort startup.
GITHUB_CLIENT_SECRETNoRequired. That app's client secret.
ALLOW_UNAUTHENTICATEDNoSet to 1 to run with no authentication, skipping the five variables above. Localhost development only — never on a public address.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/knahsirV/garmlink'

If you have feedback or need assistance with the MCP directory API, please join our Discord server