Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_HOSTNoHTTP bind address host.127.0.0.1
MCP_PORTNoHTTP bind address port.8080
LOG_LEVELNoStructured stderr log level.INFO
DATABASE_URLNoInventory connection URL.read-only demo SQLite URI
PROMETHEUS_URLNoPrometheus URL. Required only in HTTP mode.
MCP_SERVER_NAMENoAdvertised server name.kube-triage
PROMETHEUS_MODENoPrometheus mode: fixture or http.fixture
KNOWN_ISSUES_FILENoSanitized issue catalog../known-issues/catalog.yaml
SKILL_REGISTRY_DIRNoMarkdown skill root../skill-registry
HEALTH_RESTART_WARNINGNoRestart degradation threshold.5
HEALTH_CPU_WARNING_RATIONoCPU request ratio threshold.0.9
PROMETHEUS_CLUSTER_LABELNoPrometheus cluster label.
METRIC_STALE_AFTER_SECONDSNoMetric freshness threshold.300
PROMETHEUS_MAX_RANGE_HOURSNoMaximum timeline duration.24
PROMETHEUS_TIMEOUT_SECONDSNoHTTP request timeout.15
HEALTH_MEMORY_WARNING_RATIONoMemory request ratio threshold.0.9
INVENTORY_STALE_AFTER_HOURSNoInventory freshness threshold.168
PROMETHEUS_MIN_STEP_SECONDSNoMinimum timeline step.30
PROMETHEUS_MAX_RESPONSE_BYTESNoMaximum HTTP response body.2000000

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