How to Use the Google BigQuery MCP in Cursor

Q: Can I run a Google BigQuery SQL command directly inside Cursor?

Yes. Use Cursor's agent mode to trigger the executequery tool, which runs the SQL against your GCP project and inserts the resulting rows into your active file or chat.

Q: How does Cursor know my Google BigQuery table schemas?

Cursor calls listtables and gettable to pull the exact column definitions. This schema context allows the editor to write precise SQL queries that match your database.

Q: Does this Google BigQuery MCP Server support background job tracking in Cursor?

Yes. Cursor uses the getjob and listjobs tools to check the status of your queries, letting you monitor execution progress without leaving the editor.

Q: How do I configure this server for my Cursor project?

You add the MCP server configuration to your .cursor/mcp.json file. Once saved, Cursor's agent immediately gains access to all seven BigQuery metadata and query tools.

Feed live BigQuery data and schemas directly into Cursor agent mode to write working 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 Cursor

Create your Vinkius account to connect Google BigQuery to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Write code with live BigQuery SQL results

The `execute_query` tool pulls real BigQuery rows directly into Cursor's Composer or Chat panel. Instead of writing mock data, your Cursor agent uses actual BigQuery query results to build and test your application logic on the fly. That covers the basics. If your query is complex, the agent tracks its execution with `get_job` to let Cursor wait for the GCP database to finish processing before generating local code. This keeps your generation pipelines from breaking on slow database responses.

Generate accurate code using this Cursor MCP Server

The `get_table` and `get_dataset` tools read your BigQuery structure to guide Cursor's code generation. Because the Cursor editor knows your exact BigQuery column names, it generates SQL queries that work without syntax errors. Check the schema first. This MCP Server lets Cursor call `list_datasets` and `list_tables` to map your BigQuery project layout before writing code. This prevents the Cursor agent from guessing table names, saving you from failed BigQuery runs in your terminal.

Monitor active database jobs in the editor

The `list_jobs` tool exposes your GCP project's recent BigQuery query history directly inside Cursor. You can inspect active BigQuery query runs without switching from your Cursor window to the Google Cloud Console. Just run this to get the status. When you need details on a specific run, Cursor invokes `get_job` to pull the execution metrics. This helps you optimize your Cursor-generated code based on actual BigQuery bytes billed.

Setup guide

Set up Google BigQuery MCP in Cursor

Prerequisites

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

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Google BigQuery MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Google BigQuery transactions." If the MCP tools are loaded correctly, Cursor will call the Google BigQuery tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Yes. Use Cursor's agent mode to trigger the `execute_query` tool, which runs the SQL against your GCP project and inserts the resulting rows into your active file or chat.

Cursor calls `list_tables` and `get_table` to pull the exact column definitions. This schema context allows the editor to write precise SQL queries that match your database.

Yes. Cursor uses the `get_job` and `list_jobs` tools to check the status of your queries, letting you monitor execution progress without leaving the editor.

You add the MCP server configuration to your `.cursor/mcp.json` file. Once saved, Cursor's agent immediately gains access to all seven BigQuery metadata and query tools.

Your raw query statements, table schemas, and resulting rows are processed within the secure V8 sandbox. Cursor handles the data in memory during your active session, and credentials are never stored in your local code repository.

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