Skip to content

phuryn/product-engineering / app-stack/skills/mcp-server

mcp-server

Verified

Before adding a remote MCP server or tool to a web product, adding OAuth to it, or listing it in a directory: ship it right the first time, tests included.

FileKindSize
SKILL.mdskill md10.3 KB
receipts.mdmarkdown1.6 KB
references/clients.mdmarkdown6.6 KB
references/companion-repo.mdmarkdown10.4 KB
references/directories.mdmarkdown18.7 KB
references/server.mdmarkdown18.4 KB
references/tools.mdmarkdown17.3 KB

receipts.md

View on GitHub
# mcp-server: receipts

Each heading is a rule from `SKILL.md`, with the case that taught it.

## Build the remote MCP server and prove it before listing it.

- `Undated`: The lessons come from products built on the same stack (Next.js + Supabase + Clerk + Netlify): a live Q&A product with an authenticated server, a stdio package and an anonymous ChatGPT plugin, and a monitoring product that decided against any unauthenticated surface. They appear here only as examples.

## Authenticate every call, including `initialize`, by default.

- `Undated`: A monitoring product declined it: "we do not do MCP without authentication".

## Descriptions, titles and the server's instructions are product copy, and each sentence is a claim.

- `Undated`: One server's first independent round over rewritten descriptions found eight sentences the code did not keep, and they took five rounds to come back clean.

## Every argument has a description and every tool an `outputSchema`, and a test holds both against the real handlers.

- `2026-10`, a server without them scored 0 on both.

## Every tool carries a `title` and the hints a directory requires.

- `Undated`: OpenAI's listing check flagged a tool that closed something while declaring itself not destructive.

## `tools/list` has a size budget.

- `Undated`: Per-field output descriptions once took one server from 12 KB to 49 KB.

## Update every published package and listing after promoting a tool-surface change.

- `Undated`: Output schemas added to one hosted server never reached its package, which then offered a different surface from the one directories scored.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall