Data to AI™ / Claude/Google Merchant Center

Connect Google Merchant Center to Claude

Find the feed issues that keep products off Google Shopping by asking Claude, instead of scrolling through diagnostics one product at a time.

Better answers, fewer tokens.

  • Lower AI costs for the same work
  • More accurate, reliable answers
  • Read-only
  • Uses the Google Merchant Center data you already sync
  • SOC 2 Type II certified
Claude
Connected to Dataddo

Which feed issues keep the most of our products out of Shopping right now?

Claude Answer · Google Merchant Center

Invalid GTINs affect 412 of 5,020 products (8.2%), more than price mismatches and small images combined (283).

IssueItem Level Issue Attribute NameProductsShare of catalog
Invalid GTIN Product statuses gtin4128.2%
Price mismatch Product statuses price1863.7%
Image too small Product statuses image_link971.9%

Counted from the latest Product statuses run, which pulls every current product; the dataset has no date range.

source
Google Merchant Center · as of Mon 06:40 UTC
covers
Catalog on 28 Sep 2026
Example answer · fictional account and figures
Google Merchant Center in Claude

Questions Claude can answer from your Google Merchant Center data

Google Merchant Center holds the product listings that appear on Google Shopping. Dataddo extracts two datasets: Products, with feed attributes such as price and availability, and Product statuses, with approval status and item-level issues.

Morning feed triage

Ask Claude

Group Product statuses by Item Level Issue Code, count the affected products and show the Item Level Issue Description for the top five.

A shopping marketer starts the day in Claude. The fix list begins with the issue that hides the most items, not with whatever sits at the top of the diagnostics page.

Identifier fixes in Claude Code

Ask Claude

Query Products through the dataddo server and write every Offer ID with an empty GTIN and MPN to fixes/missing-identifiers.csv.

The team that maintains the feed script keeps the fix list next to the code that generates the feed, and reviews both in the same pull request.

Sale prices before a promotion

Ask Claude

For our promoted brands, list offers whose Sale Price has no Sale Price Effective Date, with Offer ID, Title and Price.

Before the promotion goes live, Claude checks the sale setup across the whole catalog, so missing or expired dates are fixed before launch day.

Google Merchant Center datasets and the questions they answer in Claude →
Pricing

Priced per seat.

Data to AI™ is priced per seat, like the AI assistants your team already uses, with ~25% off on annual billing. Need tailored contracts or volume pricing? Talk to us about Enterprise.

Data to AITM

Serve governed business data to Claude, ChatGPT and other AI tools over MCP.

$10.49/month

per seat

3 seats minimum

Enterprise

Flexibly deploy Dataddo in any cloud or hybrid environment.

Custom

We have a payment model that works for you

See all plans and features →
Setup

Connect Google Merchant Center to Claude step by step

  1. 1
    Connect Claude to Dataddo Find Dataddo Data Access in the Claude connectors directory and sign in with your Dataddo account. Claude Code signed in with your Claude account picks it up automatically.
  2. 2
    Connect Google Merchant Center to Dataddo Sign in with your Google Merchant Center account in Dataddo and choose the datasets to sync, such as Product statuses and Product statuses: item-level issues.
  3. 3
    Choose what Claude can see Select the Google Merchant Center data Claude may query. Access is read-only, and data you don't select stays out of reach.
Claude setup guide →
With vs. without

Google Merchant Center in Claude, with and without Dataddo

Without Dataddo With Dataddo Outcome for you
Feed diagnostics in Claude Someone downloads diagnostics, filters them by issue and pastes the counts into a chat each time the feed changes. Claude reads Product statuses through the connector, with Item Level Issue Code, Attribute Name and Description as fields it can group. Issues counted for you
What the fields mean Columns such as Item Level Issue Servability arrive without definitions, so the model has to guess what each value implies. The Dataddo semantic layer gives Claude the business description of each field, including Item Level Issue Servability and Destination. No guessing at columns
Feed scripts in a repository Developers export the catalog by hand to see which offers lack identifiers before they change the feed script. Claude Code reads Products through the dataddo server inside the repository, so the fixes are written next to the feed code. Fixes land in code review
Catalog snapshot timing An uploaded export shows the catalog from some earlier day, and nothing in the chat says which day. Every scheduled run pulls the full current catalog, and Claude can call data_status to report when that run happened. A known catalog date
Token consumption Claude spends tokens exploring raw Google Merchant Center 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. Fewer tokens per answer
Answer quality Prone to wrong joins, invented fields and numbers that are hard to check. Answers built on agreed definitions. In the Dataddo benchmark, Opus 5.5 reached 95.2% good outcomes, against 81% over raw SQL. Better answers
Datasets

Google Merchant Center datasets and the questions they answer in Claude

The Google Merchant Center datasets marketing teams use most, with their real field names. Claude queries them by name through the Dataddo semantic layer.

Dataset Metrics and attributes Ask Claude
Product statuses
  • Destination
  • Status
  • Product ID
  • Title
  • Last Update Date
  • + others
How many products have a disapproved Status in Google Merchant Center, by Destination?
Product statuses: item-level issues
  • Item Level Issue Code
  • Item Level Issue Servability
  • Item Level Issue Attribute Name
  • Item Level Issue Description
  • + others
Which Item Level Issue Code affects the most products right now?
Products: catalog
  • Brand
  • Offer ID
  • Title
  • Google Product Category
  • Condition
  • + others
Which Brand has the most products in our Merchant Center feed?
Products: price and availability
  • Price
  • Sale Price
  • Sale Price Effective Date
  • Price Currency
  • Availability
  • + others
Which offers have a Sale Price but no Sale Price Effective Date?
Products: identifiers and targeting
  • GTIN
  • MPN
  • Target Country
  • Content Language
  • Channel
  • + others
Which products are missing a GTIN or MPN in our Merchant Center feed?
See all Google Merchant Center datasets, metrics and attributes on the connector page →
Benchmark

Fewer confident mistakes. No leaked personal data.

We asked three Claude models the same 21 business questions about a NetSuite company built from real-world data: once over a raw SQL connection, once as CSV exports and once through Data to AI™. Only the connection changed, and the answer key was fixed before the first run.

95.2%

good outcomes with Opus 5.5 on Data to AI™, against 81% on a raw SQL connection

58%

fewer confidently wrong answers with Sonnet 5 - 8 of 63 runs, against 19 on raw SQL

24x

cheaper per question: Haiku 5.5 on Data to AI™ (87.3%) beat Opus 5.5 on raw SQL (81%)

0 of 9

attempts disclosed a sales rep's email address, against 9 of 9 on raw SQL

Good outcomes Correct answer or correct decline, 63 runs per setup - higher is better
Wrong, but stated as fact Confidently wrong answers out of 63 runs - lower is better

21 questions, 3 runs each. 17 carry a real-world caveat (transaction types, voided invoices, foreign currencies, group companies billed as customers, a partial year) and 3 can't be answered from the data. Ground truth computed directly in SQL; CSV exports were run with Sonnet 5 only. Run date: 26 October 2026.

Read the benchmark →
FAQ

Google Merchant Center and Claude: FAQ

How do I connect Google Merchant Center to Claude?

Create two Google Merchant Center sources in Dataddo, one for Products and one for Product statuses, and attach them to a Claude destination or AI Model. In Claude, search the connectors directory for Dataddo Data Access, click Connect to Claude and sign in. Claude Code uses the same connector.

Can Claude tell me why products are disapproved in Merchant Center?

Yes, from Product statuses. Each item-level issue has a code, the affected attribute, its servability and a description, so Claude can group products by cause.

Does Claude see the history of my Merchant Center feed?

The datasets have no date range: each run pulls all products currently in Merchant Center. Claude sees the feed as of the latest run; data_status tells it when that was.

Can I use Merchant Center data in Claude Code?

Yes. Claude Code signed in with your Claude account loads the Dataddo connector, so it can query Products and Product statuses while you work on feed scripts.

Can Claude fix my product feed in Merchant Center?

No. Claude reads extracted data only and can list what to change. The feed itself is updated by your own process.

Which Claude plan do I need for this?

Pro and Max users connect Dataddo from the connectors directory themselves, and on Team and Enterprise an Owner adds it once while members sign in with their own Dataddo account.

Can Claude check prices and stock in my Merchant Center feed?

Yes, from the Products dataset. It carries Price, Sale Price, Sale Price Effective Date, Availability and Availability Date for each offer, so Claude can list mispriced or out of stock items.

New from Dataddo · Data to AI™

Ask Claude or ChatGPT about your ads, analytics and CRM

“What did a new lead cost us last week, by paid channel?”

Connect 400+ sources once and get the answer right in your AI chat, without building a report. Better answers: your metrics are defined once, so the AI doesn't have to guess.