How to Use the Google BigQuery MCP in VS Code Copilot

Q: Can VS Code Copilot read my Google BigQuery table schemas?

Yes. VS Code Copilot uses listtables and gettable to pull column details, ensuring the SQL it generates matches your database schema perfectly.

Q: How does the Google BigQuery MCP Server handle authentication for teams in VS Code Copilot?

You define the server in .vscode/mcp.json and commit it. Team members authenticate securely through Vinkius, granting VS Code Copilot access to the tools without sharing master GCP keys.

Share BigQuery data access across your team using VS Code Copilot and a committed MCP config.

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 VS Code Copilot

Create your Vinkius account to connect Google BigQuery to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run BigQuery queries inside VS Code Copilot

The `execute_query` tool brings live BigQuery data directly into your VS Code Copilot Chat panel. Your team can run BigQuery SQL queries and analyze the returned rows without switching between the VS Code editor and the Google Cloud Console. That covers the basics. To keep your workspace responsive during heavy BigQuery queries, VS Code Copilot tracks execution in the background using `get_job`. The Copilot agent notifies you when the query completes, ensuring your VS Code editor remains fast and unlocked.

Inspect schemas with this VS Code Copilot MCP Server

The `get_table` and `get_dataset` tools give your team-wide Copilot agent the ability to inspect BigQuery database schemas. Copilot reads the exact BigQuery table columns to write highly accurate SQL queries directly in your active VS Code workspace files. Check the schema first. This MCP Server lets VS Code Copilot map out your GCP data structure automatically by running `list_datasets` and `list_tables`. This prevents developers from guessing BigQuery table names, reducing broken queries across your team's Git commits.

Track team database jobs in your editor

The `list_jobs` tool lets VS Code Copilot inspect recent BigQuery query history and run states within your active project. Developers can check if a BigQuery query is already running or review past executions directly from the VS Code chat interface. Just run this to see the queue. When debugging a failed run, Copilot calls `get_job` to extract the exact BigQuery error messages and performance metrics. This keeps your engineering team aligned on BigQuery query costs and optimization without leaving VS Code.

Setup guide

Set up Google BigQuery MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Google BigQuery MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Google BigQuery tools listed. Try asking: "List my recent Google BigQuery transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

You ask VS Code Copilot to execute SQL in the chat. The agent uses `execute_query` to fetch the data and displays the resulting rows directly in your editor workspace.

Yes. VS Code Copilot uses `list_tables` and `get_table` to pull column details, ensuring the SQL it generates matches your database schema perfectly.

You define the server in `.vscode/mcp.json` and commit it. Team members authenticate securely through Vinkius, granting VS Code Copilot access to the tools without sharing master GCP keys.

You need VS Code version 1.96 or higher. This version supports the agent mode required to invoke the BigQuery schema and query tools.

Yes. Your SQL query strings, database schemas, and fetched table rows are transmitted through a zero-trust V8 sandbox. Authentication is handled externally by Vinkius, so no sensitive database credentials are ever written to your git 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