▌BestMCPTools.org
BigQuery MCP logo

BigQuery MCP

Natural-language querying over Google BigQuery datasets.

DatabaseFreeClaudeClaude CodeCursorVS CodeAll ModelsModerate✓ Verified
Visit Tool130 stars

Last verified: September 20, 2026

Own BigQuery MCP? Boost it to the top.✦ Upgrade to Featured

Maintenance status

No recent updates
Last code update: March 26, 2026License: MITChecked September 28, 2026

No code pushed in over six months.

How to Install BigQuery MCP

$uvx mcp-server-bigquery

Requires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.

Setup by client

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "bigquery-mcp": {
      "command": "uvx",
      "args": [
        "mcp-server-bigquery"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "bigquery-mcp": {
      "command": "uvx",
      "args": [
        "mcp-server-bigquery"
      ]
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "bigquery-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-server-bigquery"
      ]
    }
  }
}

Claude Code (terminal)

claude mcp add bigquery-mcp -- uvx mcp-server-bigquery

Add any API keys or environment variables the server's README lists.

About BigQuery MCP

The BigQuery MCP server exposes dataset and table metadata plus query execution to an AI agent, letting it answer analytical questions against warehouse data directly. The important operational detail is cost: BigQuery bills on bytes scanned, so an agent issuing exploratory queries can run up charges quickly unless you set maximum bytes billed and point it at partitioned tables. Used carefully it is one of the highest-leverage data servers available. For a lakehouse governed by Unity Catalog, connect Databricks to Claude.

BigQuery MCP is a Database MCP server designed for developers, analysts, and data teams. It enables querying and managing databases from an AI assistant by exposing schema introspection and SQL execution as MCP tools. Key capabilities include schema introspection across tables and views, parameterised sql execution, read-only and read/write modes, and structured tool calls that work cleanly inside an LLM context. It integrates with Postgres, MySQL, SQLite, MongoDB, Redis, BigQuery, and Snowflake, and is best suited for developers, analysts, and data teams who need ad-hoc analytics without a bi tool.

Key Features

  • bigquery
  • gcp
  • sql
  • data-warehouse
  • analytics

Pricing

Free: from Free (open source; GCP billing applies to queries)

Pros & Cons

Pros

  • Lets the assistant write and run real queries instead of guessing
  • Read-only mode is safe to point at production-shaped data
  • Skips most ORM and CSV-shuffling boilerplate

Cons

  • Misconfigured permissions can expose sensitive data
  • Long-running queries need explicit timeouts
  • Schema drift requires reconnecting or refreshing context

Best For

  • Ad-hoc analytics without a BI tool
  • Drafting migrations and reviewing query plans
  • Letting non-SQL teammates ask questions of a database
  • Bootstrapping internal admin workflows

Our Take on BigQuery MCP

Powerful for analytical Q&A over warehouse data, but set a maximum-bytes-billed limit first: an agent exploring unpartitioned tables is an expensive way to learn that lesson.

Frequently Asked Questions

Tags

#Database#bigquery#gcp#sql#data-warehouse#analytics