πŸ‡·πŸ‡Ί Русская вСрсия
πŸŽ“ Field guide Β· updated 2026-10-29

Your MCP server isn't hidden.
It's in someone's queue.

Everything below comes from two places: what the registries actually return, and what server maintainers wrote in public while waiting. No growth hacks, no "10x your installs", no promises about a listing nobody at GitHub has promised.

01 🎯 The gate that isn't a bug

There are two registries and they behave nothing alike. Publishing to the open one is self-service. Getting into GitHub's β€” the one that feeds the VS Code MCP gallery β€” is a manual curation step performed by GitHub.

Observed behaviour of the two registries
Open registryGitHub registry
Addressregistry.modelcontextprotocol.iogithub.com/mcp Β· api.mcp.github.com
PublicationAutomated, immediateManual curation
Versions after first acceptβ€”Sync automatically
Published criteriaSchema validityNot published
Published ETAImmediateNone
the GitHub MCP Registry now has the ability to sync versions from the open source registry, but onboarding a new server is still a manual curation process today.
347comments in one onboarding thread#1257, 2026-10-29
327participants queuing in that thread#1257, 2026-10-29
~8 morequest β†’ listing for the first server that got in#1257: 2025-10-19 β†’ 2026-06-30
0results for our own server on the GitHub sideapi.mcp.github.com, 2026-10-29
🧊

Cold truth. Being invisible in the gallery is the default state, not a defect in your code. It does not mean your server is broken, badly written or rejected. It means a human has not looked at it yet.

02 🧱 The entry that survives a curator

You cannot speed up the queue. You can remove every reason to skip you when your turn comes. These are the items that appeared as actual blockers in requests published between 2026-10-28 and 2026-10-29.

⚠️

Do not re-post your request. In that thread, one maintainer bumped repeatedly for eight months. The listing arrived after a curator picked it up β€” not after a bump. Repeated asks add noise to a queue that is read by humans, and noise is the opposite of signal.

03 🧰 Tools an agent can actually choose

A tool description is not documentation for humans. It is the entire decision surface for a model that must pick one of your tools, or none. Write it for the model, and it stays readable for people as a side effect.

🎯

One job per tool

If the name needs "and", it is two tools. An agent that must guess which half will guess wrong on the expensive half.

🏷️

Verb-first, domain-specific names

tvijo_review beats process. The name is the first token a model sees and often the only one it ranks on.

πŸ”’

Strict schemas

Reject unknown fields rather than ignore them. A silently ignored field is a wrong action the user never sees.

πŸ“¦

Bounded output

Cap bytes, rows and age. An unbounded result is a context bomb, and it will be your server that gets blamed for the truncated answer.

πŸ™ˆ

Unknown is not zero

If you don't know the amount spent, return null and say so. Returning 0 turns an unknown bill into a false receipt.

🧯

Errors are content

Every failure gets a stable code and a sentence that tells the agent what to do next. "Something went wrong" forces a retry loop you cannot see.

04 πŸ’Έ Money in an agent loop

The moment a tool can spend, the interface changes. An agent with a spend tool and no cap is a bug report waiting for a bill attachment.

{ "prompt": "Explain how to make this function easier to test.",
  "max_usd": 0.25 }

Example from Tvijo DSHREM: default per-call cap 1 USD, hard ceiling 5 USD, paid requests never retried, tokens never returned to the model.

05 🎨 Docs UX, applied to developer tools

Developer documentation is an interface. These five rules caught more real problems for us than any redesign.

πŸͺœ

1 Β· Progressive disclosure

The first screen answers "can I use this in five minutes". Schemas, edge cases and failure codes live one level down, linked, not inline. A page that starts with architecture loses everyone who was still deciding.

πŸ“‹

2 Β· Copy-paste first

A working config block before the explanation of the config block. If a reader has to assemble a config from three sections, three of them will be wrong.

❓

3 Β· The three-question test

Can a stranger answer: what does it do, what does it cost, what breaks? If one answer is missing, the page is not finished β€” no matter how pretty it is.

πŸ”Ž

4 Β· Visible state

Show the current state instead of describing it: version, sign-in state, remaining limit. A user who can see the state stops guessing and stops writing to support.

🧭

5 Β· One path, named exits

One recommended route through the page. Alternate clients and manual setups are exits from that route, not parallel tunnels at the top.

🧾

Bonus Β· Receipts over adjectives

"Fast" is an adjective. "0.2.0 published, registry active, gallery count: 0, observed 2026-10-29" is a receipt. Receipts survive reviews.

06 πŸ“£ Being quoted, not ranked

Search ranks pages. An assistant quotes sentences. The unit of work is a claim with a source and a date β€” not a keyword with a density.

πŸͺž

Rule of the second pass. If a verdict matches the wording of the question too neatly, check it again with a different instrument. Three models agreeing on the same wrong reading agree confidently.

07 πŸ“ˆ The only loop worth running

08 ⚠️ When this does NOT work

🚫

When you need the gallery tomorrow

You can't. It is a manual gate with no published ETA. If a launch depends on it, the launch is already unscheduled. Ship the manual install path as the real path.

🧲

When the product is the listing

If being visible is the whole value, the server has no independent job. A curator notices that, and so does the first user who installs it.

πŸ•³οΈ

When you cannot show a receipt

No version, no endpoint, no dated check β€” then no claim. "It works" is not evidence, and a page built from it will not be quoted.

πŸ”

When the loop is actually a bug report

If users bounce at install, no amount of AEO fixes it. Fix install first; the page only amplifies what is already there.

Want the audit for your own server?

Free, deterministic, PASS / FAIL / NOT_RUN per item, with the command that produced it. No listing promises β€” that part is not ours to give.

Open an audit request Read the registry evidence