Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoHTTP bind address (default 127.0.0.1).127.0.0.1
PORTNoHTTP port (default 8080).8080
STEAM_IDNoDefault Steam ID (17-digit or vanity) for stdio and static bearer requests.
PUBLIC_URLNoPublic HTTPS base URL (OAuth issuer). Derived from X-Forwarded-Proto + Host if unset.
CACHE_TTL_MSNoIn-memory response cache TTL in ms (default 60000).60000
OAUTH_SECRETNoOptional separate secret for OAuth AES-256-GCM tokens/codes.
STEAM_API_KEYNoSteam Web API key for stdio and static owner bearer requests.
MCP_AUTH_TOKENNoOwner bearer token and default OAuth encryption/signing secret. Required when HOST is not loopback.
ALLOWED_ORIGINSNoComma-separated browser origins permitted on HTTP.
OAUTH_CLIENT_IDNoOptional static OAuth client ID (for Gemini "Advanced features").
OAUTH_CLIENT_SECRETNoOptional static OAuth client secret (for Gemini "Advanced features").
EXECUTION_TIMEOUT_MSNoSandbox execution timeout in ms (default 30000).30000
ALLOWED_REDIRECT_HOSTSNoExtra OAuth redirect hosts besides google.com, googleusercontent.com, and loopback.
MAX_CALLS_PER_EXECUTIONNoMax SDK calls per execute_code run (default 50).50

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