Data to AI™ / Claude/Google Search Console
Ask Claude which queries and pages gained or lost clicks, where CTR lags its Position, and which pages to refresh, without exporting Search Console reports.
Less tokens, better answers.
Claude
Which blog pages lost the most clicks in September compared with August?
The CRM guide lost 1,240 clicks, down 37%, the largest drop, and now averages Position 7.8. The other two pages fell 21% and 12%.
| URL | Clicks (Sep) | Clicks (Aug) | Position (Sep) |
|---|---|---|---|
| /blog/crm-guide Daily Metrics by Page | 2,140 | 3,380 | 7.8 |
| /blog/pricing-models Daily Metrics by Page | 1,620 | 2,050 | 5.2 |
| /blog/api-basics Daily Metrics by Page | 980 | 1,110 | 6.4 |
Page rows are sampled by Google, so pages are compared with each other and not added up into a site total.
Google Search Console shows how a site performs in Google search: Clicks, Impressions, CTR and average Position by date, query, page, country and device, for the properties your account can access.
Compare Clicks and Position per URL in Daily Metrics by Page this quarter versus last, and list the queries each sliding article is losing.
Claude lines up the trend per URL with Daily Metrics by Page and Query, so the content lead knows which articles to update first and which queries to win back.
Which URLs rank between Position 4 and 10 with CTR below 2% last month? Draft two alternative titles for each one.
Pages already on page one but rarely clicked are the cheapest wins. Claude finds them and drafts title options for the editor to test on the next release.
Query Daily Metrics by Page through the dataddo server and check that URLs renamed in last week's release still collect Impressions.
A developer working in the website repository uses Claude Code to confirm that redirected or renamed pages keep their search visibility after a deployment, before anyone files a ticket.
Data to AI™ is free while in private pre-release. We onboard teams in waves and shape the product with their feedback. At launch, it will be priced like the AI assistants your team already uses. Need tailored contracts or volume pricing? Talk to us about Enterprise.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
Free during pre-release
Flexibly deploy Dataddo in any cloud or hybrid environment.
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Days still being processed | An export pulled this morning includes recent days Google is still processing, and Claude treats those low numbers as final. | The source reads a window of 4 days ago or older, so Claude analyzes days Google has finished processing. | No half-processed days |
| Property versus page numbers | CTR and Position from a property report and a page report disagree, and a pasted table gives Claude no way to tell which is which. | Daily Metrics and Daily Metrics by Page reach Claude as separate entities, so it reports property and page figures without mixing them. | Consistent CTR and Position |
| Team access in Claude | Each SEO and content person keeps a private export, and the team argues about whose numbers are right. | On Team and Enterprise an Owner adds Dataddo Data Access once, and everyone signs in with their own Dataddo account to the same flow. | One shared source of numbers |
| Token consumption | Claude spends tokens exploring raw Google Search Console columns, sampling rows and retrying until it understands the data. | Field definitions and relations are supplied up front, so the model skips the exploration and goes straight to the answer. | Less tokens per answer |
| Answer quality | Prone to wrong joins, invented fields and numbers that are hard to check. | Answers grounded in defined fields. In the Dataddo benchmark, 78.5% of questions were answered correctly, against 65.5% with plain CSV files. | Better answers |
The Google Search Console datasets marketing teams use most, with their real field names. Claude queries them by name through the Dataddo semantic layer.
List of curated datasets
Need a dataset, metric, or attribute you don't see?
Tell us what's missing and we'll add it to the connector.
Runs on the schedule you set over a relative date window. Google needs 24 to 72 hours to process data, so use a range of 4 days ago or older; the API returns up to 16 months of history.
Google Search Console connector →We asked 43 pre-registered questions of three real datasets - Google Search Console, HubSpot deals and Google Ads - and delivered the same rows to the same model in four ways. Only the data layer changed.
of questions answered correctly - the best of the four delivery methods tested
fewer confidently wrong answers - 14.0% of runs against 24.0% and 26.3%
more correct answers on messy CRM data - better on 8 questions, worse on none
Same model, prompts and rows in every condition; 759 graded runs, ground truth frozen before any run. On Google Search Console alone, documented CSV files did as well as Data to AI™ - the advantage comes from messier data such as HubSpot deals.
Read the benchmark →Create a Google Search Console source in Dataddo as a Site Owner or Site Full User, pick datasets such as Daily Metrics by Page and Query, and attach it to a Claude destination or AI Model. Add the custom connector https://headless.dataddo.com/mcp-data in Claude, or run claude mcp add in Claude Code.
Query and page data is sampled, so summing per-query rows will not match site totals, although trends match. Ask Claude for totals from Daily Metrics or the country and device datasets.
Google takes 24 to 72 hours to process Search Console data. Set the source's date range to 4 days ago or older, so Claude works with processed days.
Up to 16 months, the limit of the Google Search Console API. Load older days within that range once with a full data re-sync.
Yes. Add the server with claude mcp add, sign in with /mcp, and Claude Code queries the same entities, with credentials stored in your system keychain.
The authorized account must be a Site Owner or a Site Full User of the property. Sites Metadata then lists each Site URL with its Permission Level.
Aggregating by property counts one result per site, while aggregating by page counts each URL. CTR and Position therefore differ between the two, even though each matches Search Console.