Connect Shopify to Claude

Shopify in Claude

Claude reads the Shopify data of one Adrails workspace through the MCP server, on claude.ai and in the Claude desktop app. It reads orders, refunds and their status, customers and their order history, products, prices and inventory, and the sessions, conversion rate and checkout funnel of the store. Nothing writes back to Shopify, and each figure keeps its source and currency, so a Shopify figure sits next to Meta Ads spend without being mixed into it.

Reviewed Oct 4, 2026

Shopify tools

What Claude can ask Adrails about Shopify

What Claude can ask Adrails about Shopify
ToolWhat it returnsExample question
store_revenueRevenue of the connected stores over a period, gross, refunded and net kept apart, with the order count, in each store's own currencyWhat was net revenue last week, and how many orders?
store_ordersOrders one by one, newest first: totals, financial status, fulfilment status and line count, at most 50 per callShow me yesterday's orders that are still unfulfilled.
store_customersCustomers newest first: name, email domain, country, creation date, order count and lifetime spend, with no full email addressHow many new customers came from Germany this month, and what have they spent?
store_productsProducts with title, price range, inventory, status, type and vendor, filtered on the title if you askWhich products are low on inventory or out of stock?
metrics_dailyThe daily series the store measures: traffic, sessions, conversion rate, sales and average order value, split by product, traffic source or countryHow did conversion rate move day by day during the sale?
business_reviewA check of a calculation you state, such as a revenue reconciliation, where every number must quote a tool result or your own words from this connection's historyReconcile the revenue Meta attributes with Shopify net sales for September.

From the Adrails MCP tools reference and the Shopify integration documentation on 4 October 2026.

01

What Claude reads from Shopify

Shopify is connected once in Adrails, under Integrations, by pasting the address of your Shopify admin and allowing the read access Shopify asks for. Adrails reads orders, refunds and their status, customers and their order history, products, prices and inventory, and the sessions, conversion rate and checkout funnel of the store, and Claude reaches the same data through the MCP server, with your sign-in and inside the one workspace you chose.

In Claude, the Shopify reads come from 6 tools: store_revenue, store_orders, store_customers, store_products, metrics_daily and business_review. The table above says what each one returns and gives a question to type as it is. Every result comes back twice, as exact data for the model and as a readable table for you, so a figure Claude states can be traced to the call that produced it.

02

Connect Claude

On claude.ai and in the Claude desktop app, the connection is a custom connector. Under OAuth client, keep Use Claude's published identity, the recommended option: Adrails reads Claude's client details from the document Anthropic hosts, and there is no client ID, secret or API key to copy. On a Claude Team or Enterprise plan, an owner of your Claude organization adds the connector first, under Organization settings, then Connectors.

Every client uses the same server URL, https://adrails.ai/api/mcp, and the same sign-in: Claude registers itself, you sign in to Adrails, then choose the workspace and the permissions on the consent screen. Shopify needs nothing on the Claude side, since it is already connected in that workspace under Integrations.

  • 1. Open Customize, then Connectors, choose Add, then Add custom connector
  • 2. Name it Adrails, paste https://adrails.ai/api/mcp as the server URL and keep Use Claude's published identity under OAuth client
  • 3. Add the connector, then connect it: Adrails opens, you sign in, choose the workspace and the permissions, and choose Allow access
  • 4. In a conversation, open the plus menu, then Connectors, enable Adrails and ask your first question

03

Three questions to start with

Ask in your own words: Claude picks the tool, Adrails returns the figures, and Claude's model does the reasoning, so a tool call uses no agent credit. Each result carries the exact data in structuredContent.result and the same figures as readable tables.

A result is at most 256,000 bytes, so a long history is asked for in shorter ranges or pages. store_revenue, store_orders, store_customers, store_products, metrics_daily and business_review are the tools Claude reaches for; the table above shows what each returns.

  • What was net revenue last week, and how many orders, next to what the ads spent?
  • Which products are low on inventory while their ads still run?
  • Reconcile the revenue Meta attributes with Shopify net sales for September.

04

What stays out of reach

No tool writes to Shopify. The connector requests read access for orders, customers, products and reports, and Adrails does not use Shopify as a destination for anything. The write permissions the consent screen can offer concern ad accounts, integrations, automations, Knowledge and campaign drafts, and none of them reaches Shopify.

Each source and currency stays separate in every result: a Shopify figure is never added to a Stripe or Meta Ads one, never converted, and always named with its source, so Claude can set them side by side but cannot blur them into one total.

A read covers the whole workspace, every ad account and integration it has, and never another workspace. Customer email addresses are turned into a one-way fingerprint before they are stored, so Claude sees a name, an email domain and a country, never a readable address.

05

Permissions, cadence and limits

Read workspace data, the one permission every connection needs, covers every integration of the workspace, Shopify included. No write permission exists for Shopify, so a member and an owner read the same data, and Claude lists no tool that could change it.

Orders arrive in real time through Shopify webhooks and are reconciled every 15 minutes; customers and products are read every hour, store analytics every 6 hours. Revenue is kept in each store's own currency and never converted.

Calls on one connection run one at a time, at most 60 a minute per access token, and a connection works in the one workspace you chose at consent: to work in another, connect Claude again and choose it. Revoke Claude under Your connections on the MCP page in Adrails; removing the server in Claude does not revoke it there.

FAQ

Common questions

Does Claude need an API key for Shopify?

No. Shopify is connected once in Adrails, under Integrations, by pasting the address of your Shopify admin and allowing the read access Shopify asks for. Claude signs in to Adrails with OAuth, with no client ID or secret to copy, and tool results never contain provider credentials or Adrails tokens.

Can Claude change my Shopify data?

No. The connector requests read access for orders, customers, products and reports, and Adrails does not use Shopify as a destination for anything. Claude may still ask for your permission in the conversation before a tool call; that governs the call, and the call only reads.

How fresh is the Shopify data?

Orders arrive in real time through Shopify webhooks and are reconciled every 15 minutes; customers and products are read every hour, store analytics every 6 hours. integrations_status returns how fresh each data stream is, so Claude can check the last read before quoting a figure.

Can I connect several Shopify accounts?

Yes. store_revenue returns the revenue of every connected store, each in its own currency and never converted, and a Claude connection reads them all; Triple Whale, if you add it, needs exactly one connected Shopify store.