Shopify in Cursor

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 Cursor reaches the same data through the MCP server, with your sign-in and inside the one workspace you chose.

In Cursor, 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 Cursor states can be traced to the call that produced it.

Cursor reads remote MCP servers from a mcp.json file, .cursor/mcp.json in a project or ~/.cursor/mcp.json for every project, one entry with a url. Adrails gives out no client ID or secret, so the entry needs no auth block: the client registers itself and the sign-in happens in your browser, and Cursor's Customize page can switch the server off without removing it.

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

• 1. Add Adrails to .cursor/mcp.json or ~/.cursor/mcp.json: { "mcpServers": { "adrails": { "url": "https://adrails.ai/api/mcp" } } }
• 2. Sign in when Cursor asks: your browser opens Adrails
• 3. Choose the workspace and the permissions, and choose Allow access
• 4. Back in Cursor, check that the Adrails tools are listed and ask your first question

Ask in your own words: Cursor picks the tool, Adrails returns the figures, and Cursor'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 Cursor 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.

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 Cursor 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 Cursor sees a name, an email domain and a country, never a readable address.

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 Cursor 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 Cursor again and choose it. Revoke Cursor under Your connections on the MCP page in Adrails; removing the server in Cursor does not revoke it there.