Reads the branch, runs it in a throwaway sandbox, and leaves the review on the merge request before a human opens it.
Built for: The engineer who keeps four tabs open to finish one ticket: the repository, the error tracker, the build log and the board.
The button opens the checkout, where 6 servers and 6 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 a merge request and its diff on GitLab and leave the review as comments, rather than as a chat message somebody has to copy across.
Run the changed code in an E2B sandbox instead of on your laptop, and throw the box away with the session.
Match a new error in Sentry to the release that introduced it, so the review names the commit instead of guessing.
Open the branch preview on Netlify and move the Shortcut story when the branch merges.
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 repository side of the desk — projects, branches and merge requests over the GitLab API, which is where a review has to land to be read.
Retrieves repository information from GitHub for the projects that never moved, so the desk answers about both hosts instead of one.
Errors, issues and releases, so the review can say which release started the crash rather than inferring it from the diff.
E2B's own server runs the branch in an isolated cloud sandbox, which is what keeps generated code off the machine you are reading it on.
Creates and reads the branch deploy through Netlify's API and CLI — the thing a reviewer opens before approving a front-end change.
The story the branch belongs to, from Shortcut's official server, so the board and the merge request stop drifting apart.
Fixes the order of a review — behaviour, then tests, then style — which is the difference between a review and a rewrite request.
Requires the failing test before the fix, so a closed bug is a proven one rather than an unreproduced one.
Turns a failed dependency audit into a specific upgrade, so the red check is a task instead of a wall of advisories.
Reads the failed GitHub Actions job for the branch and names the cause, instead of rerunning the job to see if it passes this time.
Writes the description and the diagram that go on the merge request, in the markdown the repository already uses.
Recovers the reasoning behind the code being changed — the rejected alternative, the workaround — so a review does not quietly undo a deliberate decision.
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 |
|---|---|---|
| Gitlab | Free | — |
| Github | Free | — |
| Sentry | Free | — |
| E2B (official) | Free | — |
| Netlify | Free | — |
| Shortcut (official) | Free | — |
| Skills | ||
| Code Review and Quality | $45 · $3.75/mo over 12 months | $3.75/mo |
| Test-Driven Development | $99 · $8.25/mo over 12 months | $8.25/mo |
| Audit Dependencies | $69 · $5.75/mo over 12 months | $5.75/mo |
| Fix CI Failures | $12 · $1.00/mo over 12 months | $1.00/mo |
| Markdown and Mermaid Writing | Free · context cost only | — |
| Keep the Why | $79 · $6.58/mo over 12 months | $6.58/mo |
| Everything above | $0 of servers plus $25 of skills, the same in a quiet month and a busy one | $25/mo |
Subscriptions at their monthly plan price; one-off licences spread over 12 months. One-off purchases in this stack total $304 — Code Review and Quality $45, Test-Driven Development $99, Audit Dependencies $69, Fix CI Failures $12, Keep the Why $79 — 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: 6 servers and 1 skill, 1 of the 1 tools.
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 pr-deskNothing in this stack installs from one command today: 12 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 |
|---|---|---|
| Github | not imported | not recorded |
| Gitlab | not imported | not recorded |
| Netlify | not imported | not recorded |
| Sentry | not imported | not recorded |
| Shortcut (official) | 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 6 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 — Markdown and Mermaid Writing. 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.
A team on Bitbucket gets the same shape — pull requests, branches, repositories — from a server that speaks its own host instead of GitLab's.
If the previews already build on Vercel, keep that one: the branch preview is the only thing this stack asks of either.
Written by the maintainer, kept on the page rather than in a support thread.
It cannot deploy to production. Netlify here builds the branch preview; the production deploy stays a human decision.
Nothing in it writes to your database. A migration inside the diff is read and reviewed, never run.
Every member is a record imported from a public registry, so the tool surface is not counted for this stack — each member's own page says what it declares.
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.
Takes a green branch to a running deployment, and keeps the DNS, the cluster and the access list honest on the way.
Reads the Figma file, builds the component, and ships the page without redrawing the design in CSS by eye.
Turns a bug report into a reproduction that fails, before anybody writes a line of the fix.