Answers the funnel question with the query it ran, the caveat attached, and the readout already written.
Built for: The product manager who can describe the metric they want and does not want to wait two days for it.
The button opens the checkout, where 5 servers and 4 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.
Ask Metabase for an existing question rather than writing a new query that disagrees with it.
Read event data from Mixpanel or Amplitude and say what the funnel did, week over week.
Check an experiment properly — significance, sample ratio mismatch, the tests that were not planned.
Put the numbers into a sheet with the pivot and the chart, and the readout into a deck.
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 questions and dashboards the company already trusts, so an answer matches the one on the wall instead of competing with it.
Product event data where the funnel and retention questions are actually answered.
The same analysis for teams instrumented against Amplitude, so the desk fits either shop.
Read-only access to the application database, for the questions the event stream cannot answer because it never recorded them.
Where the numbers become a pivot, a chart and a tab somebody else can open without a login.
Holds an experiment readout to significance, sample ratio mismatch and the pre-registered metric, which is where most confident wrong results come from.
The traffic side of the same picture — sessions, sources and behaviour — for questions that start before the sign-up.
The instrumentation half: adding the events that make the next question answerable instead of discovering the gap again.
Builds the readout deck from the analysis, so the last hour of an analysis is not spent formatting slides.
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 |
|---|---|---|
| Metabase | Free | — |
| Mixpanel | Free | — |
| Amplitude | Free | — |
| Postgres | Free | — |
| Google Sheets Advanced | Free | — |
| Skills | ||
| A/B Test Analysis | Free · context cost only | — |
| Google Analytics Analysis | Free · context cost only | — |
| Frontend Analytics Events | Free · context cost only | — |
| PPTX | Free · context cost only | — |
| Everything above | $0 of servers plus $0 of skills, the same in a quiet month and a busy one | $0/mo |
Subscriptions at their monthly plan price; one-off licences spread over 12 months. 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: 5 servers and 4 skills.
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 product-analyticsNothing in this stack installs from one command today: 9 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 |
|---|---|---|
| Amplitude | not imported | not recorded |
| Google Sheets Advanced | not imported | not recorded |
| Metabase | not imported | not recorded |
| Mixpanel | not imported | not recorded |
| Postgres | 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 5 members of 5 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.
1 skill in this stack instructs the agent to write — Frontend Analytics Events. A skill holds no permission of its own; it can only ask a server that already has the scope, and the approval gate still applies.
A stack is a default, not a verdict. These are the substitutions the maintainer would make, and what each one costs or saves.
Teams whose events land in a warehouse rather than in the application database read them there, with key-pair or SSO authentication and no write path.
A company whose charts live in Grafana instead of a BI tool queries the same dashboards from this desk, and loses the saved-question layer that keeps definitions shared.
Written by the maintainer, kept on the page rather than in a support thread.
It cannot fix instrumentation from here. It can tell you an event is missing or double-counted; adding it is a change in your front end.
The warehouse connection is read-only, so a data-quality bug is found here and corrected somewhere else.
It does not decide what a metric means. Two definitions of active user stay two definitions until a person picks one.
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.
Writes the migration, proves it on a branch, and says what it will do to the table before it touches the real one.
Turns a bug report into a reproduction that fails, before anybody writes a line of the fix.
Designs the endpoint, wires the auth and the payment, and reviews the shape before it is public and permanent.