How to Use the Google BigQuery MCP in Claude Code

Q: Can Claude Code handle complex SQL joins using Google BigQuery?

Yes, Claude Code uses gettable to inspect multiple table schemas and then constructs complex SQL joins. It executes them via executequery and displays the formatted results in your terminal.

Run headless database pipelines and automate BigQuery tasks directly from your terminal using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google BigQuery MCP to Claude Code

Create your Vinkius account to connect Google BigQuery to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Google BigQuery with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe BigQuery Data to Terminal Tools

The `execute_query` tool allows Claude Code to run SQL commands and pipe the output directly into grep, jq, or local shell scripts. This fits perfectly into your CLI workflow, letting you script complex data pipelines without writing boilerplate Python code. Because Claude Code lives in the terminal, it uses `list_tables` to quickly discover schemas and format the output as raw text or JSON. You get instant access to your warehouse data without leaving your SSH session.

Headless Job Management via Claude Code MCP Server

The `list_jobs` tool gives your terminal agent the power to monitor active query executions running in your GCP project. If a pipeline is stuck, Claude Code checks the status and diagnoses the bottleneck using command-line commands. When troubleshooting, the agent calls `get_job` to inspect error logs and performance metrics. This makes it easy to debug failing queries in CI/CD environments or cron jobs without logging into a web UI.

Automate Database Schema Documentation

The `get_dataset` tool lets Claude Code pull dataset metadata and write it directly to markdown files in your repository. You can run a single command to document your warehouse structure and commit the changes to Git. By combining `list_datasets` and `get_table`, Claude Code uses this MCP Server to act as an automated schema auditor. It detects drift, checks column types, and warns you about missing descriptions during your deployment checks.

Setup guide

Set up Google BigQuery MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see google-bigquery-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Google BigQuery transactions." It will automatically discover and invoke the available Google BigQuery tools.

Terminal

claude mcp add --transport http google-bigquery-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Google BigQuery MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "google-bigquery-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Google BigQuery. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Google BigQuery now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Google BigQuery MCP in Claude Code

Yes, Claude Code can run headlessly in GitHub Actions or Docker containers. You can trigger SQL queries using `execute_query` and pipe the results to other automated steps.

Claude Code uses your local gcloud CLI configuration or a service account JSON key. The MCP Server detects these credentials automatically, allowing secure access to your datasets.

Yes, Claude Code uses `get_table` to inspect multiple table schemas and then constructs complex SQL joins. It executes them via `execute_query` and displays the formatted results in your terminal.

The bq tool requires you to write every SQL statement manually. This setup lets Claude Code analyze your request, write the SQL, debug errors, and format the output autonomously.

Yes, your SQL queries, table schemas, and job execution logs are processed locally through this secure MCP Server setup. No data is sent to third-party servers, keeping your GCP compliance intact.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript