Why connect BigQuery to ChatGPT?
Many teams switched on the GA4 export and then never used it, because every question needs SQL. With Lemonado picked in ChatGPT, you ask in plain words and it queries BigQuery for you, then puts the result next to live spend from Google Ads or Meta.
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 ChatGPT
Before you start
- A Google BigQuery account you can sign in to
- A ChatGPT account
- A Lemonado account (the free trial works)
- 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
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.
texthttps://mcp.lemonado.io/mcp - 3
Open ChatGPT plugins
Go to chatgpt.com/plugins. Select + and choose Add custom MCP server.
- 4
Add Lemonado
Name it Lemonado, add a short description, and paste the server URL under Connection. Set authentication to OAuth.
texthttps://mcp.lemonado.io/mcp - 5
Create the plugin
Review the acknowledgement and select Create as a plugin. Check the tools ChatGPT discovers, then install it.
- 6
Ask ChatGPT about BigQuery
Start a new chat, type @ and pick Lemonado. Sign in to Lemonado when ChatGPT asks. Try "@Lemonado From our GA4 export in BigQuery, how many users added to cart yesterday but didn't buy, and what were they looking at?" Or ask: "Can you summarize the month?" or "Are new users buying?"
Good to know
- Your ChatGPT account and workspace settings decide whether you can add custom MCP servers. Workspace admins can turn it off.
- Older guides point to Settings → Apps → Developer mode. OpenAI has replaced that flow with Plugins.
What can ChatGPT do with BigQuery?
ChatGPT reads your BigQuery numbers when you pick @Lemonado, and writes the update, the summary or the next step for you.
ChatGPT@Lemonado From our GA4 export in BigQuery, how many users added to cart yesterday but didn't buy, and what were they looking at?
1,860 users added to cart without buying. 44% had a tent in the cart, and the most common last page was the shipping costs page.
Source: BigQuery
@Lemonado Write a short October summary from the GA4 export: sessions, purchases, revenue and the three biggest traffic sources.
October: 412k sessions, 8,140 purchases, $1.2M revenue. Top sources: Google organic, Google paid search and the newsletter.
Source: BigQuery
@Lemonado Purchases from first-time users vs returning users each week this quarter, from the GA4 export.
New users make 58% of purchases but only 41% of revenue. Returning users' share of revenue has grown every week since September.
Source: BigQuery
@Lemonado From the Search Console export, which landing pages get the most clicks, and what's their purchase rate in the GA4 export?
The tents category page gets 9,400 clicks and converts at 3.1%. The camping checklist gets 14,000 clicks but converts at 0.4%.
Source: BigQuery
Using the GA4 export, which first-touch campaigns brought users who purchased twice or more within 90 days?
The spring "Trail kit" email brought the most repeat buyers: 22% bought again. Paid social first touches came back at 9%.
Source: Google BigQuery
Compare Meta link clicks by day this month with sessions from facebook / paid in the GA4 export.
Meta reports 18,400 link clicks, the export has 11,900 sessions. The gap widened on the 9th, when an ad started pointing to a slow landing page.
Source: BigQuery + Meta
Connect BigQuery to another AI app.
Claude
Connect BigQuery to Claude
Claude Code
Connect BigQuery to Claude Code
Cursor
Connect BigQuery to Cursor
VS Code (GitHub Copilot)
Connect BigQuery to VS Code (GitHub Copilot)
Codex
Connect BigQuery to Codex
Perplexity
Connect BigQuery to Perplexity
Google Antigravity
Connect BigQuery to Google Antigravity
Windsurf (Devin Desktop)
Connect BigQuery to Windsurf (Devin Desktop)
Zed
Connect BigQuery to Zed
n8n
Connect BigQuery to n8n
Other integrations for ChatGPT
All ChatGPT integrations
Google Analytics in ChatGPTAsk Claude, ChatGPT or Cursor about GA4 traffic, conversions and funnels, next to your ad spend.
Snowflake in ChatGPTAsk Claude, ChatGPT or Cursor about the numbers in your Snowflake warehouse, with live ad spend next to them.
Google Ads in ChatGPTAsk Claude, ChatGPT or Cursor about your Google Ads campaigns, search terms and spend.
Google Search Console in ChatGPTAsk Claude, ChatGPT or Cursor about your search queries, rankings and lost clicks.
Google Tag Manager in ChatGPTAsk Claude, ChatGPT or Cursor what's in your GTM container, and what changed when tracking broke.
Pipedrive in ChatGPTAsk Claude, ChatGPT or Cursor about your Pipedrive deals, and which ads bring the ones that close.
Reading this as an AI agent?
Everything an agent needs to set this up, in plain text. Paste this page's link into ChatGPT and ask it to connect you, or copy the block.
# Connect Google BigQuery to ChatGPT (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 ChatGPT: Plugins → + → Add custom MCP server ```text https://mcp.lemonado.io/mcp ``` One-click install: https://chatgpt.com/plugins/plugin_asdk_app_69455664de448191bc42a9f6584d34e5 First question to try: "@Lemonado From our GA4 export in BigQuery, how many users added to cart yesterday but didn't buy, and what were they looking at?" More: https://lemonado.io/integrations/bigquery · https://lemonado.io/llms.txt
Frequently Asked Questions
Yes. Google runs a hosted BigQuery MCP server that ChatGPT can use once your Cloud project has it on and your user has the right IAM roles. Lemonado is one sign-in with Google, and it also brings your ad platforms, so ChatGPT can join BigQuery data with live spend.
Yes. Google's BigQuery MCP server is hosted, so ChatGPT 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 ChatGPT can answer questions across them.
Check that Lemonado is installed at chatgpt.com/plugins, then pick it with @ in a new chat. Workspace admins can turn custom plugins off. 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 "Compare Meta link clicks by day this month with sessions from facebook / paid in the GA4 export."
MCP is included in Lemonado's paid plans and in the free trial, so you can try it before you pay.
Still have a question?
Shoot us an email at hello@lemonado.io.
Try for freeStop fighting with data. Start feeding your AI.
Connect your data to AI and free your team from reporting and busywork.
Try Lemonado free