Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DATABASE_URLNoCompose sets Postgres. `memory` is for tests.memory
GEMINI_MODELNoUsed when `LLM_PROVIDER=gemini`.
LLM_PROVIDERNo`openai` or `gemini` to swap the planner.mock
OPENAI_MODELNoUsed when `LLM_PROVIDER=openai`.
GEMINI_API_KEYNoUsed when `LLM_PROVIDER=gemini`.
OPENAI_API_KEYNoUsed when `LLM_PROVIDER=openai`.
ACMG_DEMO_TOKENNoBearer token for `/mcp` in demo auth mode.demo-shopper-token
GEMINI_BASE_URLNoUsed when `LLM_PROVIDER=gemini`.Gemini's OpenAI-compatible endpoint
OPENAI_BASE_URLNoUsed when `LLM_PROVIDER=openai`.
PAYPAL_API_BASENoReserved for the PayPal sandbox adapter.
PUBLIC_BASE_URLNoIssuer and MCP resource URL in OAuth metadata.http://localhost:4317
MCP_INTERNAL_URLNoWhere the agent loop calls the server.http://127.0.0.1:4317/mcp
PAYMENT_PROVIDERNo`paypal` selects the sandbox seam, which still refuses live calls.mock
PAYPAL_CLIENT_IDNoReserved for the PayPal sandbox adapter.
PAYPAL_CLIENT_SECRETNoReserved for the PayPal sandbox adapter.

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