How to Use the Google BigQuery MCP in Windsurf

Q: Can Cascade write queries autonomously using the Google BigQuery MCP Server in Windsurf?

Yes, Cascade uses gettable to pull the schema first, then writes and runs the SQL via executequery. It handles the entire chain from schema discovery to data retrieval without requiring manual prompts for each step.

Q: What happens if a Google BigQuery query fails in Windsurf?

Cascade catches the error, uses getjob to inspect the job details, and corrects the SQL syntax. It then runs the query again, showing you the final working output directly in your workspace.

Query massive Google BigQuery datasets and map schemas directly inside Windsurf using Cascade's autonomous multi-step reasoning.

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 Windsurf

Create your Vinkius account to connect Google BigQuery to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Explore Dataset Schemas via Windsurf

The `list_datasets` tool lets Cascade scan your active GCP project to map out your entire data warehouse structure. Instead of jumping to the Google Cloud Console, your Windsurf agent inspects dataset structures natively to plan its next steps. Once Cascade finds the target dataset, it uses `get_dataset` to understand the tables within it. It acts as an autonomous planner, gathering structural data so it knows exactly what fields are available before writing any code.

Direct SQL Execution with Cascade Chains

The `execute_query` tool runs standard SQL commands right inside the Windsurf terminal or editor pane. Cascade chains this tool with local workspace files, allowing it to pull live data and immediately write it into your local Python or TypeScript files. If a query takes too long, Cascade uses `get_job` to monitor the execution state. This keeps your editor responsive while the agent waits for BigQuery to finish processing gigabytes of data.

Inspect Tables and Jobs via Windsurf MCP Server

The `get_table` tool retrieves column details, types, and descriptions so Cascade writes correct SQL on the first try. You avoid syntax errors because the agent reads the schema directly through this MCP Server before drafting queries. To keep track of active operations, Cascade uses `list_tables` and `list_jobs` to verify your workspace remains in sync with GCP. It handles the back-and-forth of database discovery so you can focus on analyzing the results.

Setup guide

Set up Google BigQuery MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Google BigQuery payment history." If connected, Cascade will call the Google BigQuery tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Windsurf reads your GCP credentials from the environment or a service account key file. Once configured in your Windsurf MCP settings, Cascade handles the handshake automatically, so you never have to hardcode keys.

Yes, Cascade uses `get_table` to pull the schema first, then writes and runs the SQL via `execute_query`. It handles the entire chain from schema discovery to data retrieval without requiring manual prompts for each step.

Cascade catches the error, uses `get_job` to inspect the job details, and corrects the SQL syntax. It then runs the query again, showing you the final working output directly in your workspace.

Standard extensions require you to write every query manually. This server gives Cascade the tools to discover schemas, write SQL, and parse results on its own.

Your SQL queries, table schemas, and job metadata never leave your local machine or your secure Vinkius sandbox. Windsurf communicates directly with the BigQuery API using your local GCP credentials, keeping your enterprise data locked down.

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