Dataki for Google Search Console
Ask Google Search Console in plain English
Ask Search Console questions in plain English. The bulk data export puts every query and page in BigQuery, with no 1,000-row cap, and Dataki charts clicks and rankings from it.
Through BigQuery The bulk data export to BigQuery. The guide takes about 10 minutes.
Which pages lost the most clicks last month, compared with the month before?
/blog/sql-joins lost 1,940 clicks in August, the biggest drop on the site.
01Questions
What people ask Google Search Console
Each one becomes a query against the Google Search Console data, run read-only, with the SQL shown beside the chart so anyone who reads SQL can check it. Anything worth keeping goes on a dashboard that refreshes on its own.
- Which pages lost the most clicks compared with last month?
- Which queries rank between positions 5 and 15 with the most impressions?
- How did clicks from mobile change after the last release?
- Which new queries appeared this week?
02From your assistant
Ask Google Search Console from Claude, ChatGPT or Cursor
Dataki runs a hosted MCP server. Add it to your assistant once and it can read the Google Search Console data in BigQuery and run read-only queries through Dataki. The assistant gets the rows back; the credentials stay encrypted in Dataki and never reach the model.
Setup for your assistant:
From the Search Console export, which pages lost the most clicks this month, and on which queries?
- list_sources · finds BigQuery · searchconsole
- get_data_context · reads the tables and what the columns mean
- query · runs the SQL read-only, returns the rows
- render_ui · draws the chart from those rows, in the chat
https://dataki.ai/api/mcp 03Setting it up
Getting Google Search Console data to Dataki
The bulk data export to BigQuery. The setup guide covers it step by step.
- Setup
- About 10 minutes, then up to 48 hours for the first export.
- Cost
- The export is free, but needs a Cloud project with billing. BigQuery storage and queries are billed beyond the free tier.
- History
- From the day you set it up. Earlier data stays in Search Console.
- You need
- Owner of the Search Console property, and a Cloud project where you can grant IAM roles.
Live dashboards
Every answer can become a live dashboard.
Ask in plain English. Dataki writes the SQL, runs it on your database and charts the answer. Keep it as a dashboard with its own link, and your team sees current numbers every time they open it.
3 views · Updated just now
One click turns the answer into a dashboard:
Always current. The query runs again whenever the dashboard opens, so Friday's meeting sees Friday's numbers.
- Share it
- Send the link to anyone. Viewers are free on every plan.
- Refine it
- The SQL is always visible. Adjust it by hand or ask for a change.
- Embed it
- Put the same dashboard in your own product with two HTML tags.
Using Dataki with Google Search Console
- Can I query Google Search Console in plain English instead of writing SQL?
- Yes. Dataki works with Google Search Console through its BigQuery dataset (The bulk data export to BigQuery). Ask in plain English and Dataki writes the SQL against that dataset, runs it and returns a chart. The query is shown with every result, so you can check or edit it.
- How do I build a dashboard from Google Search Console data without an ETL pipeline?
- Follow the Google Search Console setup guide once and your data lands in BigQuery automatically, with no pipeline to maintain. Connect that dataset to Dataki, ask your question and save the answer as a dashboard widget. Dataki queries the dataset live, so the dashboard is always as fresh as the export.
- Can Claude, ChatGPT or Cursor query my Google Search Console data?
- Yes, through Dataki's hosted MCP server at https://dataki.ai/api/mcp. Connect Google Search Console to Dataki, add that URL as a connector in Claude or ChatGPT (or in Cursor, VS Code or Claude Code with a Dataki key), and your assistant can read the schema and run read-only queries. It works with the results, while your credentials stay encrypted in Dataki and never reach the model.