Turns the ticket, the thread and the source into a page somebody can follow, in the words your product already uses.
Built for: The writer maintaining documentation for a product that ships faster than the docs do.
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 the Jira issue and the Confluence page behind a change and write the update from both.
Publish into Notion or Confluence, in the structure the space already uses rather than a new one.
Crawl the public source a page is documenting and quote it accurately.
Produce the diagram, the deck and the cover image the page needs without leaving the desk.
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 issue behind the change, which is where the reason for a documentation update is usually written down first.
The space the page belongs in, read and written in place instead of pasted from a draft.
The other half of the same job for companies whose documentation lives in Notion.
The source of truth for anything technical: the code, the README and the commit that changed the behaviour being documented.
Searches and reads the specifications and decks that never became documentation, which is where most missing pages already exist in draft.
Scrapes the external source a page cites, so a quote is checked rather than remembered.
One markdown convention and diagrams as code, which is what keeps a documentation set consistent across writers.
Applies plain writing rules to text people have to follow under pressure — the difference between a page that works and a page that is complete.
Keeps API terminology consistent across pages, which is where technical documentation quietly contradicts itself.
For the long-form technical paper a docs team is asked for once a quarter: structure, paragraph flow, and a reviewer's reading of it.
Produces the diagram, cover or one-page PDF a document needs, without a round trip through a design team.
The exact identity-platform term, endpoint or environment variable, for the authentication pages that are wrong in every product's documentation.
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 |
|---|---|---|
| Jira | from $25/mo | $25/mo |
| Confluence | from $25/mo | $25/mo |
| Notion | Free | — |
| Gitlab | Free | — |
| Google Drive (official) | Free | — |
| Firecrawl | Free | — |
| Skills | ||
| Markdown and Mermaid Writing | Free · context cost only | — |
| Write Concisely | Free · context cost only | — |
| OpenAPI Glossary | $59 · $4.92/mo over 12 months | $4.92/mo |
| Research Paper Writing | $45 · $3.75/mo over 12 months | $3.75/mo |
| Canvas Design | Free · context cost only | — |
| WorkOS | $59 · $4.92/mo over 12 months | $4.92/mo |
| Everything above | $50 of servers plus $14 of skills, the same in a quiet month and a busy one | $64/mo |
Subscriptions at their monthly plan price; one-off licences spread over 12 months. One-off purchases in this stack total $163 — OpenAPI Glossary $59, Research Paper Writing $45, WorkOS $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: 4 servers and 3 skills, 0 of the 28 tools.
Left out, and what goes with it:
Jira at from $25/mo and Confluence at from $25/mo. Each of those plans states the calls it includes in a month, and running past one never arrives as a larger invoice: the gateway refuses the call over the allowance and returns an MCP error naming the plan. The figure above is what the stack costs in a busy month as well as a quiet one — what a heavy month changes is which plan you need, not what this one bills.
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 docs-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 |
|---|---|---|
| Firecrawl | not imported | not recorded |
| Gitlab | not imported | not recorded |
| Google Drive (official) | not imported | not recorded |
| Notion | 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 4 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.
Teams whose issues live in Linear read the reason for a change there, and the Atlassian half of the desk disappears with it.
Where the sources are single pages rather than sites, plain fetching is enough and there is no crawl to pay for.
Written by the maintainer, kept on the page rather than in a support thread.
It cannot decide what is true. Where the code and the ticket disagree, the desk shows both and a person resolves it.
It does not own terminology on its own. The glossary skill enforces consistency once you have decided the words.
Both Atlassian members are community-maintained and not affiliated with Atlassian, which matters when your instance is on a version they have not followed.
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.
Finds the sources, keeps what it read, and answers with a citation that still opens next quarter.
Reads the branch, runs it in a throwaway sandbox, and leaves the review on the merge request before a human opens it.
Writes the migration, proves it on a branch, and says what it will do to the table before it touches the real one.