Skip to main content
Glama
vjh0107
by vjh0107

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_PATHNoBase path for the MCP endpoint./mcp
MCP_PORTNoPort for the HTTP server.3000
POD_NAMENoName of this process, used in logs and metrics. Defaults to the pod hostname.
MCP_BIND_HOSTNoHost/address to bind the HTTP server to.0.0.0.0
MCP_LOG_LEVELNoLog level: debug, info, warn, error.info
MCP_TRANSPORTNoTransport mode for the MCP server. Values: http or stdio.http
MCP_AUTH_TOKENNoIf set, requests must include this Bearer token in the Authorization header. If unset, authentication is disabled.
SA_AUTH_ALLOWEDNoComma-separated list of allowed service accounts in 'namespace:name' format. If empty, any authenticated ServiceAccount is allowed.
SA_AUTH_ENABLEDNoWhether to enable Kubernetes ServiceAccount token authentication.false
SHUTDOWN_DRAIN_TIMEOUT_SECONDSNoMaximum seconds to wait for in-flight tool calls during shutdown.30
SHUTDOWN_READINESS_GRACE_SECONDSNoSeconds to keep serving after SIGTERM before removing from endpoints.5

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