A laptop showing a Shopify store's product and order cards, linked by a connector to a friendly AI assistant

Shopify MCP Server: What It Does and How to Connect Shopify to AI in 2026

Yes — Shopify has an official MCP server. In fact it has several. Shopify’s own connector apps for Claude and ChatGPT, launched in May 2026, let a merchant read and write real store data — orders, prices, inventory, discounts — straight from a chat. A separate Dev MCP server, open-sourced as part of Shopify’s AI Toolkit, helps developers build Shopify apps and themes. So if you’re searching “Shopify MCP,” the connection you want already exists — no third-party workaround required.

The thing worth knowing before you set it up: an MCP connection hands your store to an AI inside a conversation you start. It’s a doorway, not a worker. Nothing watches your orders for you, nothing fires when stock runs low, and nothing runs while the chat is closed. Here’s exactly what the Shopify MCP does, how to turn it on, where it stops — and what to use when you want Shopify work that runs on its own.


What the Shopify MCP server does

Model Context Protocol (MCP) is the open standard that lets an AI client — Claude, ChatGPT, Cursor, VS Code, and others — talk to an outside app through a shared interface. Shopify maintains several official servers, but two are what people usually mean:

  • Claude and ChatGPT connector apps (built and maintained by Shopify, launched May 2026) — install directly inside Claude or ChatGPT, connect your existing store, and the AI gets read and write access to your Shopify Admin data: orders, products, inventory, discount codes, customers, and analytics.
  • Dev MCP server (@shopify/dev-mcp, open-sourced April 2026 as part of the Shopify AI Toolkit) — runs locally and gives coding agents like Claude Code, Cursor, and VS Code access to Shopify’s API schemas, documentation, and code validation for building apps and themes.

Shopify also publishes Storefront, Customer Account, and Checkout MCP servers, but those are for building AI shopping agents that serve your customers on your storefront — not for you to manage your own store from a chat. For most people searching “Shopify MCP,” it’s the Claude/ChatGPT connector apps that matter. With one connected, you can:

  • Look up orders — “show me today’s unfulfilled orders over $100” answered from live data.
  • Adjust products and inventory — raise a price, move stock across locations, without opening the admin.
  • Create discount codes — spin up a promo on the spot.
  • Pull performance — ask how a collection sold this week and get a real answer.

It’s genuinely useful for ad-hoc work: ask a question, get an answer grounded in your store, make a change on the spot.

How to set up the Shopify MCP server

The merchant-facing connector is the quick path — no code, no hosting:

  1. In Claude, go to Settings → Connectors and find Shopify (or visit claude.ai/directory/connectors/shopify). In ChatGPT, install the app from chatgpt.com/apps/shopify.
  2. Authenticate with your Shopify account and approve the access level — you’re granting the AI read-only or read/write access to one store at a time.
  3. Start a chat and ask it to pull an order or update a listing.

The Dev MCP server runs differently — add npx @shopify/dev-mcp@latest to Claude Code, Cursor, or VS Code’s MCP config. It doesn’t touch your store data at all, so there’s no Shopify authentication step; it only serves documentation, schemas, and validation for people writing Shopify code.

Where the Shopify MCP stops

None of this is a knock on MCP — it’s just the shape of the protocol. Four limits show up the moment you want more than a conversation:

  • It only works inside a chat you start. Close the window and nothing happens. The AI doesn’t watch your store; it waits for you to ask.
  • No triggers. An order coming in, stock dropping below a threshold, a return being requested — none of these can start anything through MCP. There’s no “when this happens in Shopify, do that.”
  • It’s one app at a time. The Shopify connector knows Shopify. Getting a new order into Slack, a spreadsheet, and your accounting tool means wiring up a separate MCP connection for each, then hoping your client can juggle them in one turn.
  • You own the plumbing and the scopes. The access level you approve — and the blast radius of letting an AI write to your live store — is on you.

So the Shopify MCP is a great way to ask your store things and make one-off edits. It is not a way to make Shopify run — to have work happen on a schedule or in reaction to an event, across the other tools an order touches.

Running Shopify work that doesn’t need a chat open

That “run on its own, across apps” gap is exactly where Carly fits. Carly connects to Shopify natively — no connector to install, no MCP config to maintain — and to the ~260 other apps it supports, plus anything with a public API through your own key. The difference from MCP is the important part: Carly’s workflows are triggered and scheduled, so Shopify work happens whether or not anyone has a chat window open.

A few things that MCP can’t do but a Carly workflow can:

  • When an order over $500 comes in → tag the customer as VIP, post to the #big-orders Slack channel, and log it in a spreadsheet — automatically, the moment it happens.
  • Every morning → summarize yesterday’s sales, flag any product below your stock threshold, and email the list to the owner.
  • When inventory hits zero on a bestseller → draft a reorder email to the supplier for approval.

The non-AI steps — the moving, matching, and routing between apps — are free and unlimited, the Zapier-style backbone of the workflow. The AI steps (drafting, summarizing, deciding) start at $35/month. You describe the outcome in plain language and Carly wires up the Shopify connection and everything downstream.

If you just want to ask your store questions from a chat, Shopify’s official connector apps are the right tool and they’re free to connect. If you want Shopify to actually do things — on a trigger, on a schedule, across every app an order flows through — that’s the job MCP wasn’t built for, and it’s the one Carly was.

FAQ

Does Shopify have an official MCP server? Yes. Shopify builds and maintains the connector apps for Claude and ChatGPT (launched May 2026), which give those AI tools read/write access to your store’s orders, products, inventory, and discounts. Shopify also ships a separate open-source Dev MCP server for developers building apps and themes.

Is the Shopify MCP connector free? Connecting the Claude or ChatGPT app is free — you’re authorizing an AI client against your existing Shopify account. You still need whatever Shopify plan your store runs on.

Can the Shopify MCP trigger automations? No. MCP is request/response inside an AI chat — it has no triggers and nothing runs when the conversation is closed. For event- or schedule-driven Shopify work across apps, you need a workflow tool like Carly rather than an MCP connector.

What AI tools can connect to Shopify over MCP? Claude and ChatGPT both have official Shopify connector apps for store management. Developers building on Shopify can also use the Dev MCP server from Claude Code, Cursor, and VS Code.

Can I connect Shopify to AI without coding or hosting a server? Yes. You don’t have to touch MCP at all. Carly connects to Shopify for you and lets you build the automation in plain language — describe what you want to happen and it wires up the Shopify connection and the other apps involved, with no server to host and no code to write.

Ready to automate your busywork?

Carly schedules, researches, and briefs you—so you can focus on what matters.

See what people say

"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.

Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.

On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."

Gus Ibrahim, Founder & Director, IHR