Product and catalog management
Create and update products, variants, and collections; fix the pricing errors and description drift that quietly cost conversions; changes shown as before-and-after first.
Shopify connector
Shopify MCP Connector – Orders, Products and Customers on Demand
For e-commerce marketers, the store is the scoreboard, and the scoreboard lives behind Shopify admin: orders in one report, products in another, the customer answer three exports away. Meanwhile the ad platforms spend all day making promises the store has to keep.
The Shopify connector puts the scoreboard in the conversation. It links the AI you already use, like Claude, ChatGPT, or Copilot, to your store through Mad Fish Elements, with typed operations for products, orders, customers, collections, inventory, discounts, and fulfillments, plus the full GraphQL and REST Admin API behind them. Ask what sold. Fix what is listed wrong. See the store and the spend in the same sentence.
See it
What Your AI Can See
Connect your store, and your AI reads commerce the way you ask about it: orders over any window with their values and statuses, products with their variants and inventory, customers with their history, collections, discounts, and fulfillment states.
The daily questions become sentences. "What sold yesterday, and what is trending this week?" "Which products are low on inventory with ads still running?" That second one is the money question, because the same Gateway reads your ad platforms: spend on one side, stock and sales on the other, one answer. "Which discount codes actually drove orders?" reads promotion truth. "Who are our repeat customers this quarter?" reads the base the next campaign should court.
Anything the typed reads do not cover, the full Admin API does, GraphQL included, so the store's whole surface is in reach of a question.
Do it
What Your AI Can Do
With Write access and your approval, your AI operates the catalog and commerce records:
Inventory awareness and updates
Read stock across locations and adjust where your flow calls for it, so the ads-versus-inventory collision gets caught before customers find it.
Discount management
Create and manage the codes and automatic discounts campaigns depend on, named right, scoped right, expiring when they should.
Order and fulfillment operations
Read deeply, and where your ops flow warrants, update records and fulfillments, on approval, in the audit trail.
Full Admin API reach
GraphQL and REST passthrough for everything else, from metafields to the odd report, governed by the same permissions.
A working session
The Promo That Launched Correct
In practiceThe session before every promotion: the weekend sale starts Friday. You ask, "Create a 20% discount code SUMMER20 for the summer collection, active Friday through Sunday." Shown, approved, created. Then the check that saves promotions: "Which products in the summer collection are under 20 units in stock?" Three, and one is the hero product in the ads. You ask, "What is the ad spend pointed at that product this week?" The Gateway reads Meta and Google: enough spend to sell it out by Saturday morning. You shift the hero creative to the deep-stock alternative before launch. The promo runs clean, because the store and the spend finally talked to each other.
The return
What You Get Back
Ads and inventory in one view
The spend-versus-stock collision caught before it becomes a customer-facing apology.
Catalog changes with receipts
Prices, descriptions, and collections updated on approval, with before-and-after in the trail.
Promotion truth
Which codes drove orders, which margins survived, which discounts leaked.
Commerce answers at marketing speed
What sold, who bought, and what to push next, without the export ritual.
Use cases
One Conversation, Real Account Work
"What sold this week, top 10 by revenue?"Shopify
The scoreboard as a visual report, live from the store.
"Which products are under 20 units with active ad spend?"Shopify · Meta · Google Ads
The stock-versus-spend collision report, in one pass.
"Create the SUMMER20 code for the summer collection, this weekend only."Shopify
The promotion built on approval, scoped and expiring correctly.
"Which discount codes drove the most orders last quarter, and at what revenue?"Shopify
Promotion truth, ranked and checkable.
"Update the pricing on these five products to the new list."Shopify
Catalog changes shown as before-and-after, shipped on your yes.
For in-house teams
Close the expectation gap
The marketer running the ads finally sees the store the ads point at, in the same conversation. Promotions launch checked, catalogs stay correct, and the merchandising-to-marketing gap closes.
For marketing teamsFor agencies
Run the whole book
E-commerce clients judge you on revenue, not clicks. Read client stores under per-client permission walls, report spend beside sales in numbers that reconcile, and catch the out-of-stock hero product before the client's customers do.
For agenciesReports worth sharing
From Live Account to Clear Story
Ask in chat and share the dashboard without building exports or taking screenshots.
Revenue Scoreboard
Sales, orders, and top products, any window. Built for the daily check and the client call.
Stock-vs-Spend Board
Low-inventory products against live ad spend. Built for promo weeks.
Promotion Performance Report
Codes and discounts by orders and revenue. Built for the post-promo review.
The charts do the talking: line for revenue trend, bar for product ranking, table-first for order detail. And when your leaders or clients want these anytime, the Data Visualization add-on turns your reports into always-current dashboards they open from a link. Ask in chat; share the dashboard.
The useful signals
The Numbers That Matter
Commerce keeps honest score. Revenue and orders by day and week: the pulse. Top products: where the money actually concentrates, usually more narrowly than anyone guesses. Inventory against spend: the collision number, checked before every promotion. Discount performance: orders and revenue by code, so promotions get judged, not just remembered fondly. Repeat customer share: the base the next campaign should court first. And average order value, the quiet lever under everything. The habit: pulse daily, collision check before flights, promotion review after them. Every one is a question here, and the store's answers reconcile with admin because they are admin, asked politely.
A practical start
Your First Week
Day one: connect the store and read the scoreboard. "Top ten products by revenue this week." Day two: run the collision check. "Products under 20 units with active ad spend." This is the question that saves promotions. Day three: make one catalog fix; pick a stale description or a wrong price. Approve the before-and-after; day four: read promotion truth. "Which discount codes drove orders last quarter?" Day five: schedule the rhythm. "Daily, the revenue scoreboard; before promos, the stock-versus-spend check." By Friday, the store and the spend are in the same conversation for the first time, the catalog is a little more correct, and the next promotion will launch checked instead of hopeful. The scoreboard was always there; now it answers.
Works best with
Build the Connected View
Pair Shopify with Meta and Google Ads for the spend-versus-stock collision check and the revenue-per-channel truth. Add Mailchimp for email revenue against the same orders, and GA4 for the on-site path between click and cart. Commerce is the scoreboard every other connector plays toward.
Clear limits
What This Connector Will Not Do
It will not touch your theme or storefront code; it operates commerce data through the Admin API, not your site's design. It will not change prices, products, or discounts without approval, and every change carries a name in the audit trail. It will not invent sales numbers; the scoreboard is the store's own. And it will not reach stores you did not connect.
Governance
Governed Access Your Whole Org Can Live With
Access is set per person, not per account, so Read seats see everything and change nothing while Write seats create and edit with your approval flow in front of every change. Delete access goes only to people you trust to clean up, and many teams start read-only, check answers against the platform, then widen access as the audit trail earns it.
You choose the level of human review and can change it at any time, while every action records what changed, when, and who approved it. Per-user access means Elements never stores your Shopify password, and your data is never harvested or resold.
Per-user accessRead / write / delete per seatFull audit trailApproval flow on every change
Setup
Setup Takes Minutes
- Start your trialCreate your Elements account and connect it to your AI.
- Link ShopifySign in through the secure connection screen and choose what to connect. No code and no engineers.
- Set permissionsDecide who can Read, who can Write, and who can Delete. Start conservative and widen as trust builds.
- Ask your first question"How did we do last month?" is a complete instruction.
Plans, account limits, and the multi-client Agency plan are on the pricing page .
FAQ
Shopify Connector Questions
Does it cover our whole Admin API surface?
Yes: typed operations for the commerce core, and full GraphQL plus REST passthrough for everything else the Admin API exposes, under the same permissions and approvals.
Can it process refunds or edit orders?
Order and fulfillment operations are available under Write permissions and approval where your ops flow wants them. Most teams start with catalog, discounts, and reporting, and keep order surgery with the ops staff.
How current is the data?
Live at the moment you ask, from the Admin API. The scoreboard matches admin because it is admin, asked politely.
Will my AI change things without asking me?
No. Your AI acts only with the permissions you set, and changes follow the review level you choose. Read-only seats cannot change anything, because the approval flow is the product working as designed.
Which AI assistants can our team use?
Your team can use Claude, ChatGPT, and Microsoft Copilot, while other AI tools can likely connect when they support MCP, the open standard for linking AI assistants to outside tools.
Is my data used to train anything?
No. Your data stays yours, so nothing is harvested and nothing is resold.
Focus on the Strategy, Delegate the Launch
The teams winning with AI are not handing their accounts to a black box; they keep the strategy and delegate the hands-on-keyboard work, while approvals and an audit trail make it safe to move fast. Connect the account you already have through the Gateway and ask the question you would normally build a report to answer.
Your first 14 days are free. Add your card to start, and cancel before the trial ends to pay nothing.