Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MQTT_ENABLEDNoSet to 'true' to enable MQTT subscription for device status, telemetry, logs, fault, and heartbeat topics.false
MODEL_CACHE_MODENoModel cache mode: 'download' allows fetching missing models from the network; 'offline' blocks downloads and fails readiness if the cache is incomplete.download
DIAGNOSIS_LLM_MODELNoModel identifier for the external LLM used for complex diagnosis.
DIAGNOSIS_LLM_API_KEYNoAPI key for the external LLM used for complex diagnosis (if unset, heuristic fallback is used).
DIAGNOSIS_DATABASE_PATHNoPath to the SQLite database used as the local source of truth.data/iot_diagnosis.db
DIAGNOSIS_MCP_PUBLIC_URLNoPublic URL of the MCP server, used by clients and required when a bearer token is set.
DIAGNOSIS_MCP_BEARER_TOKENNoIf set, the MCP endpoint requires this Bearer token for authentication.
DIAGNOSIS_SYNC_RETRY_SECONDSNoInterval in seconds for retrying failed MySQL/Qdrant writes via the persisted outbox.
DIAGNOSIS_RETRIEVAL_MODEL_HEALTH_URLNoHealth check URL for the retrieval model service, used by the /ready endpoint.

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