Skip to content
Try for free

Connect BigQuery to VS Code

  • Can you update the KPI doc?

Ask GitHub Copilot in VS Code to join raw events to ad cost, with live BigQuery data in agent mode. Lemonado connects them in about 2 minutes, no API keys needed.

Try free with $150 in creditsJump to the steps
MCPhttps://mcp.lemonado.io/mcp

Why connect BigQuery to VS Code (GitHub Copilot)?

Copilot's agent mode can call MCP tools inside your workspace, so it can read live numbers while it edits code and docs. Connected through Lemonado, it reads your BigQuery GA4 events, datasets, tables and scheduled queries, so it can join raw events to ad cost with today's numbers.

  • All your BigQuery data

    Datasets and tables your account can read, ready to ask about.

  • Always today's numbers

    Google Ads and Search Console bulk exports, if you run them, synced from BigQuery automatically, so answers use today's numbers.

  • Connect all your tools

    Questions like "What did paid sessions earn?" use BigQuery and GA4, Snowflake at once.

How to connect BigQuery to VS Code (GitHub Copilot)

Before you start

  • A Google BigQuery account you can sign in to
  • VS Code installed
  • A Lemonado account (the free trial works)
  1. 1

    Connect Google BigQuery in Lemonado

    In Lemonado, open Connectors, find Google BigQuery and sign in. Sign in with a Google account that can read the dataset holding your GA4 export, and pick that project. The BigQuery Data Viewer and Job User roles are enough.

  2. 2

    Turn on external access

    In the company's settings, open External tools, turn the connection on, choose which sources it can reach and copy the server URL.

    text
    https://mcp.lemonado.io/mcp
  3. 3

    Add the server

    With AI features on and a project open, run MCP: Add Server from the command palette. Choose HTTP, paste the server URL and name it lemonado.

    text
    https://mcp.lemonado.io/mcp
  4. 4

    Choose where it lives

    For your personal Copilot setup, choose Global → Copilot Global. That writes to ~/.copilot/mcp-config.json unless COPILOT_HOME says otherwise.

  5. 5

    Trust and sign in

    Accept the trust prompt and sign in to Lemonado. Turn the tools on under Chat: Open Customizations → Tools.

  6. 6

    Ask VS Code (GitHub Copilot) about BigQuery

    Try "Update the table in docs/kpis.md with last month's BigQuery numbers and add one line on what changed." Or ask: "Flatten purchases" or "Save sessions by source"

Good to know

  • The older .vscode/mcp.json format still works for the local harness, but VS Code now marks that destination as deprecated. It uses a servers key with type http and the same URL.

What can VS Code (GitHub Copilot) do with BigQuery?

Copilot reads your BigQuery data in agent mode and works the numbers into your code, docs and notebooks in the workspace you have open.

VS Code (GitHub Copilot) logoVS Code (GitHub Copilot)

Update the table in docs/kpis.md with last month's BigQuery numbers and add one line on what changed.

Updated docs/kpis.md with last month's numbers next to the month before, plus a line on the biggest change and its cause.

Source: Google BigQuery + your code

Connect BigQuery to another AI app.

Other integrations for VS Code (GitHub Copilot)

All VS Code (GitHub Copilot) integrations

Reading this as an AI agent?

Everything an agent needs to set this up, in plain text. Paste this page's link into VS Code and ask it to connect you, or copy the block.

For agents · markdown
# Connect Google BigQuery to VS Code (Lemonado MCP)

- Server URL: https://mcp.lemonado.io/mcp
- Transport: Streamable HTTP
- Auth: OAuth; the user signs in to Lemonado in the browser. No API keys.
- In Lemonado: connect the Google Cloud project. Sign in with a Google account that can read the dataset holding your GA4 export, and pick that project. The BigQuery Data Viewer and Job User roles are enough.
- In VS Code: Command palette: MCP: Add Server

```text
https://mcp.lemonado.io/mcp
```

First question to try: "Update the table in docs/kpis.md with last month's BigQuery numbers and add one line on what changed."

More: https://lemonado.io/integrations/bigquery · https://lemonado.io/llms.txt
FAQ

Frequently Asked Questions

Yes, through Lemonado. Connect your Google Cloud project in Lemonado, add Lemonado with MCP: Add Server in VS Code, and VS Code can join raw events to ad cost with your live data.

Yes. Google's BigQuery MCP server is hosted, so VS Code can use it too. It covers Google BigQuery only. Lemonado covers Google BigQuery plus your ad platforms, GA4 and the rest of your stack in one connection, so VS Code can answer questions across them.

Run MCP: List Servers from the command palette. If lemonado isn't running, start it there, accept the trust prompt and sign in. In Lemonado, check that Google BigQuery is connected and External tools is on for the company. If yesterday's GA4 data is missing, the daily export may not have landed yet. GA4 writes the events_ table for a day several hours after it ends.

Yes, if both are connected in Lemonado. One connection reaches every source you allow, so you can ask things like "Join GA4 purchase revenue from BigQuery with Google Ads cost by campaign for last month."

MCP is included in Lemonado's paid plans and in the free trial, so you can try it before you pay.

See plans and pricing

Still have a question?

Shoot us an email at hello@lemonado.io.

Try for free

Stop fighting with data. Start feeding your AI.

Connect your data to AI and free your team from reporting and busywork.

Try Lemonado free