BigQuery MCP server: list datasets and tables, read schemas, run SELECT queries with a byte limit.
Maintain this server? Claim it
This server only runs locally, from a package. Install it with the instructions on this page to try it.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add bigquery-mcp \ -- npx -y @renzo.johnson/[email protected]
Environment
GOOGLE_APPLICATION_CREDENTIALS (optional, not in the config above): Path to a service account key or authorized_user JSON file. Optional if you use gcloud Application Default Credentials or the OAuth variables.GOOGLE_OAUTH_CLIENT_ID (optional, not in the config above): OAuth client ID. Set together with the client secret and refresh token.GOOGLE_OAUTH_CLIENT_SECRET (optional, not in the config above): OAuth client secret.GOOGLE_OAUTH_REFRESH_TOKEN (optional, not in the config above): OAuth refresh token with the BigQuery scopes.BIGQUERY_MCP_PROJECT_ID (optional, not in the config above): Google Cloud project ID used when a request does not name one.BIGQUERY_MCP_MAX_BYTES_BILLED (optional, not in the config above): Largest number of bytes a query may scan (default 1000000000).We don't run packages, so we can't list this server's tools.