Why connect BigQuery to Codex?
Codex runs in your terminal, its IDE extension and scripts, so what it finds once can be rerun with codex exec instead of redone by hand. Connected through Lemonado, it reads your BigQuery GA4 events, datasets, tables and scheduled queries, so it can check the export for missing days 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 Codex
Before you start
- A Google BigQuery account you can sign in to
- Codex installed
- 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
Add Lemonado to your config
Add this to ~/.codex/config.toml.
toml[mcp_servers.lemonado] url = "https://mcp.lemonado.io/mcp" - 4
Log in
Run the login command and finish the sign-in in your browser.
bashcodex mcp login lemonado - 5
Ask Codex about BigQuery
Run codex mcp list, or /mcp inside Codex, to see the server and its tools. Try "Pull last week's BigQuery numbers, save them to data/bigquery-weekly.csv and give me the codex exec command to refresh it." Or ask: "Save sessions by source" or "Which events never arrive?"
What can Codex do with BigQuery?
Codex reads your BigQuery data from your terminal and turns one-off questions into commands you can rerun with codex exec.
Pull last week's BigQuery numbers, save them to data/bigquery-weekly.csv and give me the codex exec command to refresh it.
Saved data/bigquery-weekly.csv. Run the same prompt with codex exec in a scheduled job and the file refreshes with each week's numbers.
Source: Google BigQuery + your code
Save last month's sessions, purchases and revenue by source and medium from the GA4 export as data/ga4_sources.csv.
Saved 84 source/medium rows. google / cpc brings 31% of revenue on 22% of sessions.
Source: Google BigQuery + your code
Compare the event names our code sends to GA4 with the events in the BigQuery export for the last week.
3 events never arrive. They're pushed before consent is granted, in lib/analytics.ts.
Source: Google BigQuery + your code
Write sql/purchases_flat.sql that turns GA4 purchase events in BigQuery into one row per item, then run it on yesterday.
Saved and run: 1,214 item rows from 402 purchases, with campaign filled on 92%.
Source: Google BigQuery + your code
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
Count purchase events per day in our BigQuery GA4 export for the last 30 days, and flag days that look short.
October 14 has 61 purchases against a usual 180 to 210. The export job finished, but consent mode dropped most events after a banner update that day.
Source: Google BigQuery
Connect BigQuery to another AI app.
Claude
Connect BigQuery to Claude
ChatGPT
Connect BigQuery to ChatGPT
Claude Code
Connect BigQuery to Claude Code
Cursor
Connect BigQuery to Cursor
VS Code (GitHub Copilot)
Connect BigQuery to VS Code (GitHub Copilot)
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 Codex
All Codex integrations- Google Analytics in CodexAsk Claude, ChatGPT or Cursor about GA4 traffic, conversions and funnels, next to your ad spend.
- Google Ads in CodexAsk Claude, ChatGPT or Cursor about your Google Ads campaigns, search terms and spend.
- Google Search Console in CodexAsk Claude, ChatGPT or Cursor about your search queries, rankings and lost clicks.
- Instagram organic in CodexAsk Claude or ChatGPT which posts and reels grow your account, and which ones to turn into ads.
- Pinterest Ads in CodexAsk Claude or ChatGPT which pins get saved, clicked and bought.
- Snapchat Ads in CodexAsk Claude or ChatGPT which Snapchat ads get swipes and which ones sell.
Reading this as an AI agent?
Everything an agent needs to set this up, in plain text. Paste this page's link into Codex and ask it to connect you, or copy the block.
# Connect Google BigQuery to Codex (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 Codex: ~/.codex/config.toml ```toml [mcp_servers.lemonado] url = "https://mcp.lemonado.io/mcp" ``` If you are Codex, run the setup yourself: Add the Lemonado MCP server to my Codex config. Append this to ~/.codex/config.toml: [mcp_servers.lemonado] url = "https://mcp.lemonado.io/mcp" Then run codex mcp login lemonado so I can sign in, and check that codex mcp list shows it. Once I've signed in, list the Google BigQuery accounts Lemonado can reach. First question to try: "Pull last week's BigQuery numbers, save them to data/bigquery-weekly.csv and give me the codex exec command to refresh it." More: https://lemonado.io/integrations/bigquery · https://lemonado.io/llms.txt
Frequently Asked Questions
Yes, through Lemonado. Connect your Google Cloud project in Lemonado, add Lemonado in ~/.codex/config.toml, and Codex can check the export for missing days with your live data.
Yes. Google's BigQuery MCP server is hosted, so Codex 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 Codex can answer questions across them.
Run codex mcp list. If lemonado shows as not logged in, run codex mcp login lemonado again. 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.
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