Publishing 9 Aug 2026 · 3 min read

How to publish an MCP server people actually install

The code is the easy half. What separates a listing with installs from one without is a short list of things that have almost nothing to do with your server working.

MR mcprush team · The people who run the gateway

Most first listings are a working server and a paragraph. They collect a handful of installs, and their publisher concludes the market is small. The market is not small. The listing is doing one job when it needs to do three: convince a person, satisfy a scanner, and stay legible to a model that will be reading those tool descriptions in six months without you there to explain them.

The path a listing takes. Most of the delay is at review, and most of what review finds is dull.The path a listing takes. Most of the delay is at review, and most of what review finds is dull.
The path a listing takes. Most of the delay is at review, and most of what review finds is dull.

Your tool surface is the product page

A buyer with any judgement reads which of your tools write before they read your description. Which makes tool naming and tool reach not an implementation detail but the first impression.

The cheapest change most listings can make, and the one that turns a hard decision into two easy ones.The cheapest change most listings can make, and the one that turns a hard decision into two easy ones.
The cheapest change most listings can make, and the one that turns a hard decision into two easy ones.
  • Split the tool that both reads and writes. One half becomes safe to grant, and you have made the decision easier for every reader.
  • Name them for what they do to the world, not for what they do in your codebase. create_issue, not handle_request.
  • Do not ship a tool you cannot describe in one line. If it takes a paragraph, it is two tools or it is a bad tool.

If your server declares thirty tools, the honest question is whether it is one server or four. Four listings each with a legible surface will outperform one with a wall of them — and each is easier to review, easier to grade and easier to trust.

What a listing has to answer, in order

Three questions, in this order. A listing that answers them in a different order loses people between them.Three questions, in this order. A listing that answers them in a different order loses people between them.
Three questions, in this order. A listing that answers them in a different order loses people between them.

Nobody scrolls a listing they have not decided about yet. The first two sentences decide whether the rest gets read, and "what it reaches" belongs above the feature list rather than below it.

A free tier is not generosity, it is the funnel

Of everything a publisher controls, opening free moves installs most — and the mechanism is not that engineers are cheap. An engineer evaluating four servers will install the three that cost nothing to try. The fourth never gets evaluated; not rejected, evaluated.

Make it a real allowance rather than a countdown. A trial is a deadline the buyer has to plan around; an allowance is a habit that forms while they are not thinking about you.

Write the description twice

  • For a person: what it does, what it reaches, what it costs — in the first two sentences.
  • For a model: tool descriptions that state preconditions and failure modes plainly. "Returns 404 if the project does not exist" prevents a retry loop; "gets project info" causes one.

The second audience is the one publishers forget, and it decides whether your server feels reliable. A model that knows what your errors mean will report them; a model that does not will retry them, and the buyer will call that flakiness in a review that stays up forever.

Same code, same uptime, different review. The description is doing the work.Same code, same uptime, different review. The description is doing the work.
Same code, same uptime, different review. The description is doing the work.

What review is looking for

What review findsWhy it holds the listing
A tool whose reach is wider than its description impliesThe description is what the buyer consented to
A manifest that does not match the handshakeThen the printed surface is fiction
A dependency with a known problemIt ships to every install at once
Credentials scoped wider than the tools useThe most common finding, and almost always an accident
The last row surprises people every time. It is usually an OAuth scope list copied from somewhere else and never trimmed.

After it is live

  • Answer reviews. An unanswered one-star is the last thing a buyer reads before deciding.
  • Ship the second version. A listing untouched for months reads as abandoned, whatever the code is doing.
  • Watch what gets called. The tools nobody calls are the ones to cut — and cutting them narrows your surface, which raises the grade and shortens the next review.

And read your own error rate the way a buyer does. Publishers see "99% success". Buyers see the one call in a hundred that made their agent do something stupid, and that is the one they write about.