Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MASTER_KEYYesMaster encryption key used to encrypt/decrypt sensitive configuration values. Required.
FHIR_BASE_URLNoFHIR base path (e.g. /fhir/R4).
LOINC_ENDPOINTNoLOINC API search endpoint (e.g. https://loinc.regenstrief.org/searchapi/loincs).
LOINC_PASSWORDNoLOINC account password. Can be stored encrypted (EncryptedField).
LOINC_USERNAMENoLOINC account username.
TRANSPORT_MODENoSet transport mode for the server: stdio, http, or https.
EMBEDDING_MODELNoHugging Face embedding model name (e.g. NeuML/pubmedbert-base-embeddings).
FHIR_SERVER_HOSTYesFHIR API host URL (e.g. https://api.medplum.com).
PINECONE_API_KEYNoPinecone API key for vector search / document search. Can be stored encrypted (EncryptedField).
FHIR_SERVER_CLIENT_IDYesOAuth2 client ID for the FHIR server.
FHIR_SERVER_CLIENT_SECRETYesOAuth2 client secret for the FHIR server. Can be stored encrypted (EncryptedField).

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