Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PHI_MODENoEnable PHI queries (default false)
BACKEND_TYPENoDatabase backend: bigquery, snowflake, or duckdb
MAX_COST_USDNoMaximum cost for BigQuery queries (default 1.0)
OAUTH_ISSUERNoOAuth issuer URL
DUCKDB_SCHEMANoDuckDB schema (default main)
OAUTH_AUDIENCENoOAuth audience
SNOWFLAKE_USERNoSnowflake username
SNOWFLAKE_SCHEMANoSnowflake schema name (e.g., cdm)
SNOWFLAKE_ACCOUNTNoSnowflake account identifier
ALLOW_PATIENT_LISTNoAllow patient ID queries in production (default false)
ATHENA_TIMEOUT_SECNoATHENA API timeout (default 60)
SNOWFLAKE_DATABASENoSnowflake database name
SNOWFLAKE_PASSWORDNoSnowflake password
BIGQUERY_DATASET_IDNoBigQuery dataset ID (e.g., omop_cdm)
BIGQUERY_PROJECT_IDNoGCP project ID for BigQuery
SNOWFLAKE_WAREHOUSENoSnowflake warehouse name
DUCKDB_DATABASE_PATHNoDuckDB database path (default :memory:)
OMOP_BLOCKED_COLUMNSNoComma-separated list of blocked PHI columns
MAX_QUERY_TIMEOUT_SECNoQuery timeout in seconds (default 30)
STRICT_TABLE_VALIDATIONNoEnable strict table allowlist validation (default false)
BIGQUERY_CREDENTIALS_PATHNoPath to service account JSON file (optional, use ADC if empty)

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/aandresalvarez/omop-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server