BigQuery MCP Server

Databasestdiov0.9.0

MCP server for Google BigQuery that lets AI agents explore datasets, inspect table schemas, and run SQL analytics queries with dry-run cost estimation. Useful for natural-language data analysis, ad-hoc reporting, and pipeline debugging against large-scale BigQuery warehouses.

bigquery google-cloud sql analytics data-warehouse reporting

Connect

Add this configuration to .claude/mcp.json

{
  "mcpServers": {
    "bigquery": {
      "command": "uvx",
      "args": [
        "bigquery-mcp"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "<YOUR_GOOGLE_APPLICATION_CREDENTIALS>",
        "BIGQUERY_PROJECT": "<YOUR_BIGQUERY_PROJECT>"
      }
    }
  }
}

Tools (3)

execute_query

Run a SQL query against BigQuery and return the result rows.

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "Standard SQL query to execute"
    },
    "dry_run": {
      "type": "boolean",
      "description": "If true, estimate bytes processed without running the query"
    }
  }
}

list_datasets

List datasets available in the configured GCP project.

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "GCP project ID (defaults to configured project)"
    }
  }
}

get_table_schema

Return the schema of a BigQuery table.

{
  "type": "object",
  "required": [
    "dataset",
    "table"
  ],
  "properties": {
    "table": {
      "type": "string",
      "description": "Table name"
    },
    "dataset": {
      "type": "string",
      "description": "Dataset name"
    }
  }
}

Resources

This server does not expose any resources.

Prompts

This server does not expose any prompts.

Server Information

Author: Google Cloud Community (@googleapis)
Repository: https://github.com/googleapis/genai-toolbox
License: Apache-2.0
Version: 0.9.0
Stars: 1,500
Last Updated: June 19, 2026