Connect Shopify to ChatGPT
Shopify in ChatGPT
ChatGPT reads the Shopify data of one Adrails workspace through the MCP server, in ChatGPT with Developer mode turned on. 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 ChatGPT can ask Adrails about Shopify
| Tool | What it returns | Example question |
|---|---|---|
| store_revenue | Revenue of the connected stores over a period, gross, refunded and net kept apart, with the order count, in each store's own currency | What was net revenue last week, and how many orders? |
| store_orders | Orders one by one, newest first: totals, financial status, fulfilment status and line count, at most 50 per call | Show me yesterday's orders that are still unfulfilled. |
| store_customers | Customers newest first: name, email domain, country, creation date, order count and lifetime spend, with no full email address | How many new customers came from Germany this month, and what have they spent? |
| store_products | Products with title, price range, inventory, status, type and vendor, filtered on the title if you ask | Which products are low on inventory or out of stock? |
| metrics_daily | The daily series the store measures: traffic, sessions, conversion rate, sales and average order value, split by product, traffic source or country | How did conversion rate move day by day during the sale? |
| business_review | A 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 history | Reconcile 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 ChatGPT 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 ChatGPT reaches the same data through the MCP server, with your sign-in and inside the one workspace you chose.
In ChatGPT, 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 ChatGPT states can be traced to the call that produced it.
02
Connect ChatGPT
ChatGPT adds remote MCP servers through Developer mode, which depends on your ChatGPT plan and your workspace's policy. The server is added once, then enabled in the conversations where you want it, and ChatGPT's app settings let you switch individual tools off and refresh the list from the server.
Every client uses the same server URL, https://adrails.ai/api/mcp, and the same sign-in: ChatGPT registers itself, you sign in to Adrails, then choose the workspace and the permissions on the consent screen. Shopify needs nothing on the ChatGPT side, since it is already connected in that workspace under Integrations.
- 1. In ChatGPT Settings, turn on Developer mode
- 2. Open Plugins and add a custom MCP server named Adrails, with https://adrails.ai/api/mcp as its URL and OAuth as its authentication
- 3. Sign in to Adrails, choose the workspace and the permissions, and choose Allow access
- 4. Review the tools ChatGPT discovered, then add Adrails to a new conversation
03
Three questions to start with
Ask in your own words: ChatGPT picks the tool, Adrails returns the figures, and ChatGPT'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 ChatGPT 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 ChatGPT 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 ChatGPT 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 ChatGPT 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 ChatGPT again and choose it. Revoke ChatGPT under Your connections on the MCP page in Adrails; removing the server in ChatGPT does not revoke it there.
Go further
Read more
- ChatGPT integrationChatGPT with Adrails: setup, the 63 tools and the controls, for every source of the workspace.
- Shopify in AdrailsThe Shopify connector: which read scopes it asks for, what it synchronizes and how to remove it.
- Connect an AI clientEvery client, step by step, then how to check the connection.
- MCP tools referenceEvery tool, its inputs and who can call it.
FAQ
Common questions
Does ChatGPT 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. ChatGPT 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 ChatGPT 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. ChatGPT may still ask for your permission before a write action runs; 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 ChatGPT 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 ChatGPT connection reads them all; Triple Whale, if you add it, needs exactly one connected Shopify store.