How to Use the Google BigQuery MCP in Claude

Q: Can Claude Desktop discover my Google BigQuery schemas?

Yes. Claude Desktop calls listdatasets and listtables to see what is available, then uses gettable to inspect columns so it writes correct SQL.

Q: How does this Google BigQuery MCP Server handle long-running queries in Claude Desktop?

If a query takes time, Claude Desktop tracks it using getjob. The agent monitors the job status in the background and alerts you when the data is ready.

Query BigQuery tables and inspect dataset schemas directly from your Claude Desktop chat window.

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 Desktop

Create your Vinkius account to connect Google BigQuery to Claude Desktop 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 Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run BigQuery SQL inside Claude Desktop

The `execute_query` tool runs BigQuery Standard SQL queries directly inside your Claude Desktop chat interface. Look, the bottom line is you don't need to copy-paste data from the Google Cloud Console anymore. Your returned BigQuery rows feed directly into your Claude Desktop chat context. If a query takes a while, Claude Desktop uses `get_job` to track the execution state of your BigQuery run. It polls the job ID in the background so your Claude agent knows exactly when your BigQuery data is ready to be rendered as an artifact.

Explore datasets with this Claude Desktop MCP Server

The `list_datasets` and `list_tables` tools map out your BigQuery database structure directly inside Claude Desktop. Your Claude agent looks up what tables are available, preventing syntax errors before you run a single BigQuery query. Check the schema first. This MCP Server lets you target a table, then the agent invokes `get_table` and `get_dataset` to read the exact column names and types inside Claude Desktop. This means Claude Desktop writes accurate BigQuery SQL on the first try because it knows the schema beforehand.

Track active BigQuery jobs in chat

The `list_jobs` tool displays your GCP project's recent query history inside the Claude Desktop interface. You don't have to guess if a query is stuck. Just run this to see what's actually running right now. You can ask Claude Desktop to check on a long-running BigQuery job by passing the ID to `get_job`. The agent reads the job metadata and tells you how many BigQuery bytes were billed directly in your active Claude chat.

Setup guide

Set up Google BigQuery MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Google BigQuery MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Google BigQuery MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under google-bigquery-mcp.

json

{
  "mcpServers": {
    "google-bigquery-mcp": {
      "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 Desktop

You just ask Claude Desktop to query a table. The agent uses the `execute_query` tool to run your SQL directly against your GCP project and returns the rows to your chat.

Yes. Claude Desktop calls `list_datasets` and `list_tables` to see what is available, then uses `get_table` to inspect columns so it writes correct SQL.

If a query takes time, Claude Desktop tracks it using `get_job`. The agent monitors the job status in the background and alerts you when the data is ready.

No. The MCP server runs via Vinkius, meaning Claude Desktop connects to your BigQuery instance using a secure endpoint token without local CLI dependencies.

Your raw query statements, dataset schemas, and returned rows pass through a secure V8 sandbox. Vinkius handles the authentication tokens, ensuring your raw data never gets cached or exposed to external third parties.

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