Skip to main content
Glama
pvoo

BigQuery MCP Server

by pvoo

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GCP_PROJECT_IDYesGoogle Cloud project ID
BIGQUERY_LOCATIONYesBigQuery location (e.g., US, EU)
BIGQUERY_SAMPLE_ROWSNoSample data rows returned in get_table (default: 3)3
BIGQUERY_DISTANCE_TYPENoDistance metric for vector search: COSINE, EUCLIDEAN, DOT_PRODUCT (default: COSINE)COSINE
BIGQUERY_EMBEDDING_MODELNoFull path to embedding model (project.dataset.model) for vector search
BIGQUERY_ALLOWED_DATASETSNoComma-separated list of datasets to restrict to (default: all datasets)
BIGQUERY_EMBEDDING_TABLESNoTables with embedding columns for vector search (comma-separated)
BIGQUERY_LIST_MAX_RESULTSNoMax results for basic list operations (default: 500)500
BIGQUERY_MAX_BYTES_BILLEDNoMax bytes billed per query job (default: 109951162777)109951162777
BIGQUERY_SAMPLE_ROWS_FOR_STATSNoRows sampled for column fill rate calculations (default: 500)500
BIGQUERY_VECTOR_SEARCH_ENABLEDNoEnable or disable vector search tools (default: true)true
GOOGLE_APPLICATION_CREDENTIALSNoPath to service account key file (default: Application Default Credentials)
BIGQUERY_EMBEDDING_COLUMN_CONTAINSNoPattern for finding embedding columns (default: embedding)embedding
BIGQUERY_LIST_MAX_RESULTS_DETAILEDNoMax results for detailed list operations (default: 25)25

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/pvoo/bigquery-mcp'

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