Runs the shop's day: catalogue, prices, campaigns, and the tickets that follow them.
Built for: The operator who is merchandiser, marketer and support for the same store, most weeks alone.
The button opens the checkout, where 8 servers and 5 skills are listed one by one with what each does to the bill — free, already yours, monthly or a one-off licence. Nothing is charged until you confirm it there, in Stripe’s own card frame on that page rather than a redirect, and each paid member keeps its own budget cap.
The reason to buy a stack rather than five listings: each line below needs more than one member connected at the same time.
Read and update products, inventory and orders through the Shopify Admin GraphQL API.
Read what the store is billing through Stripe, and build the campaign that follows it in Mailchimp.
Pull the export into a sheet and analyse it, instead of scrolling admin screens.
Answer the tickets a promotion generates from the same desk that ran the promotion.
What each part contributes, and why it was picked over the obvious alternative. Prices and permissions are read from the listings, so nothing here can disagree with the catalogue.
The store's own Admin GraphQL API — products, collections, orders — which is where a storefront day actually happens.
A second route to the same API, for the queries the first server's shape does not cover comfortably.
Customers and subscriptions on the billing side, for stores selling something recurring alongside the catalogue.
The automations that carry a launch or a restock to the list that asked to hear about it.
The working surface for exports, price lists and the reconciliation that never fits in an admin screen.
Geocoding and places for delivery zones, store locators and the shipping questions a catalogue alone cannot answer.
The tickets that follow every promotion, answered from the desk that knows what the promotion was.
Reads the spreadsheets suppliers and platforms send, with pagination, so a 60,000-row export is analysed rather than opened.
Designs the discount properly — tiers, conditions, stacking rules — before it is implemented as three overlapping promotions that cost money.
The integration patterns behind subscriptions and invoices, for the part of the store that is code rather than configuration.
Abandoned cart, post-purchase and lifecycle flows written as sequences instead of as individual sends nobody measures.
Product and campaign video end to end — captions, soundtrack, export — which a small store otherwise has to buy in.
Reads pages that resist automation, for the price and availability monitoring a merchandiser does by hand otherwise.
Every member is a subscription or a licence bought once, so the monthly figure is a price rather than an estimate: what moves it is adding or dropping a member, not how hard the stack is worked. The one assumption is that a one-off licence is spread over a year so it can sit in the same column as a subscription.
| Part | What you are paying for | Monthly, as quoted |
|---|---|---|
| Shopify | Free | — |
| Shopify Admin | Free | — |
| Stripe Billing | Free | — |
| Mailchimp | Free | — |
| Google Sheets | Free | — |
| Geoapify | Free | — |
| Zendesk | Free | — |
| Excel Analyser | Free | — |
| Skills | ||
| Discount Engine | $12 · $1.00/mo over 12 months | $1.00/mo |
| Stripe | Free · context cost only | — |
| email-sequences | $59 · $4.92/mo over 12 months | $4.92/mo |
| Super Video Maker | Free · context cost only | — |
| Scrapling Official | Free · context cost only | — |
| Everything above | $0 of servers plus $6.00 of skills, the same in a quiet month and a busy one | $6.00/mo |
Subscriptions at their monthly plan price; one-off licences spread over 12 months. One-off purchases in this stack total $71 — Discount Engine $12, email-sequences $59 — paid once and spread here so they sit in the same column as a subscription. Everything arrives on one mcprush invoice, taken by Stripe from the card on your account, not one per publisher — mcprush.com is the merchant of record and each publisher is paid out of it.
Install only these and the bill is nothing: 8 servers and 3 skills.
Left out, and what goes with it:
Nothing in this stack carries a call allowance, so nothing here can run out before the month does. The bill is decided when you install it, not when you use it.
Budget caps are set per install and enforced at the gateway, so a retry loop is refused at the cap rather than left to run through an allowance overnight.
One step per part, in the order they are useful: connect what the work reads before what it writes, and install the skills that decide how the work is done last. Each step is a command you can read before you run it.
npx mcprush@latest stack add storefrontNothing in this stack installs from one command today: 13 members are either paid, run from its own source, or a skill with its own command — the steps above name each one. Nothing is connected until you approve it.
Installed together, these tool surfaces add up. It is the first thing a security reviewer asks for, so what has been counted — and what nobody has counted yet — is on the page rather than in a PDF.
| Member | Tool surface | Write tools |
|---|---|---|
| Excel Analyser | not imported | not recorded |
| Geoapify | not imported | not recorded |
| Google Sheets | not imported | not recorded |
| Mailchimp | not imported | not recorded |
| Shopify | not imported | not recorded |
| Shopify Admin | not imported | not recorded |
| Stripe Billing | not imported | not recorded |
| Zendesk | not imported | not recorded |
A stack's blast radius is the union of its members, not the worst of them. That union cannot be taken here, because 8 members of 8 have no imported tool surface — so the figure a review asks for is missing rather than low, and a member marked not imported is one nobody has counted rather than one that cannot write.
A stack is a default, not a verdict. These are the substitutions the maintainer would make, and what each one costs or saves.
Where the export work needs structural edits — new tabs, formatting, batch updates — the fuller Sheets server does it, and asks for wider Drive access in return.
For stores whose email is transactional rather than campaign-led, SendGrid covers the sends and the marketing automation goes away with it.
Written by the maintainer, kept on the page rather than in a support thread.
It cannot take a payment. Reading billing data and charging a customer are different keys, and only the first belongs here.
It does not set prices. A discount rule can be designed and written; changing a live price is an action a person signs off.
It cannot scrape a competitor's site for you legally by default. The scraping member exists for pages you are allowed to read — that judgement stays yours.
A stack has an owner: whoever keeps it re-checks the combination when a member changes, and the members themselves are published by the people named on each row.
Reads the ticket, finds whether it is a bug or a billing question, and drafts the reply in your own voice.
Reconciles what the ledger says with what the payment processor did, and writes the invoice at the end of it.
Reads the branch, runs it in a throwaway sandbox, and leaves the review on the merge request before a human opens it.