Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TIMEZONENoIANA timezone override (e.g., America/New_York). Overrides stored config and OS detection.
HTTP_HOSTNoBind address for HTTP transport. Use 0.0.0.0 only behind a reverse proxy.127.0.0.1
HTTP_PORTNoPort for HTTP transport. When set, enables streamable HTTP mode instead of stdio.
TENANT_IDNoUUID for tenant isolation
REDIS_URLSNoComma-separated Redis URLs. When set, activates Full Mode with distributed locking.
LOCK_TTL_SECSNoLock time-to-live in seconds30
ALLOWED_ORIGINSNoComma-separated allowed Origin headers for HTTP mode (e.g., http://localhost:3000). All cross-origin requests rejected if unset.
GOOGLE_CLIENT_IDNoGoogle OAuth Client ID from Cloud Console
OAUTH_REDIRECT_PORTNoPort for the local OAuth callback server8085
GOOGLE_CLIENT_SECRETNoGoogle OAuth Client Secret
GOOGLE_OAUTH_CREDENTIALSNoPath to Google OAuth JSON credentials file (alternative to CLIENT_ID + CLIENT_SECRET)

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/billylui/cortex-mcp'

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