Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoServer host.
PORTNoServer port.
LOG_LEVELNoServer log level.
QUEUE_HOSTNoRabbitMQ host. Empty QUEUE_HOST leaves this service planning only.
QUEUE_PORTNoRabbitMQ port.
QUEUE_USERNoRabbitMQ user.
CONFIG_USERNoWho this service says it is to mcp-config.
ROUTER_MODELNoThe model that picks a tool for a prompt.
OPENAI_API_KEYNoKey for ChatGPT, and for an OpenAI compatible provider with no endpoint of its own.
QUEUE_PASSWORDNoRabbitMQ password.
CONFIG_PASSWORDNoPassword for mcp-config.
OPENAI_BASE_URLNoDefault endpoint when the model names none. Empty means api.openai.com.
PUBLISHER_TOKENNoShared secret the gateway presents as X-MCP-Token. Unset means the publish routes are unauthenticated.
ROUTER_ENDPOINTNoThe endpoint of the model that picks a tool for a prompt.
ROUTER_PROVIDERNoThe provider of the model that picks a tool for a prompt.
ANTHROPIC_API_KEYNoKey for definitions whose provider is Anthropic.
CONFIG_SERVER_URLNoWhere mcp-config is.
OPEN_MODEL_API_KEYNoKey for an endpoint that is not OpenAI's. Usually empty — a local server needs none.

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

Maintenance

ActivityMaintained
ResponsivenessNo issues