Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
제작자가 쓴 설명(영어 원문)
Audit your site, pick from 1,600+ launch directories by DR and link type, and list on SaaSCity.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:
https://saascity.io/api/mcpClaude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요
{
"mcpServers": {
"saascity": {
"command": "npx",
"args": [
"-y",
"saascity-mcp"
]
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add --transport http saascity https://saascity.io/api/mcpclaude mcp add saascity -- npx -y saascity-mcp프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"saascity": {
"url": "https://saascity.io/api/mcp"
}
}
}프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"saascity": {
"command": "npx",
"args": [
"-y",
"saascity-mcp"
]
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"saascity": {
"type": "http",
"url": "https://saascity.io/api/mcp"
}
}
}프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"saascity": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"saascity-mcp"
]
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:
https://saascity.io/api/mcp메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
도구 이름과 설명은 서버가 2026년 11월 7일에 알려 준 그대로예요. 우리가 아니라 제작자가 쓴 글이고, 일반 텍스트로만 보여 드려요.
check_launch_readinessAudit a product homepage before launching it: HTTPS, noindex, title and meta description, og:image (fetched to confirm it loads), X card, favicon, canonical, mobile viewport, h1, JSON-LD, robots.txt, sitemap, parked or 404 pages, response time, and whether the page is empty witho
recommend_launch_directoriesHand-picked launch directories for a product type, grouped by when to submit (launch day first, evergreen after). Every pick carries a human-written verdict, including the ones that are not worth paying for, plus Ahrefs DR, link type and price. Start here; use find_launch_directo
find_launch_directoriesFilter 1,667 startup, SaaS and AI directories by category, minimum Ahrefs DR, link type (dofollow/nofollow), price and badge-swap requirement. Returns submit URLs. Link type and price are "unknown" where nobody has verified them yet - treat those as unverified, not as free or dof
get_launch_directoryLook up one directory by domain or URL: Ahrefs DR, dofollow or nofollow, price, whether it wants a badge swap, the submit URL, and a human verdict where one exists. Use it to vet a directory before paying for a listing.
submit_projectList a product on the SaaSCity launch directory. Creates an inert draft and returns a claim URL; the human opens it to sign in, gets the submit form prefilled with the draft, picks a plan and a launch Monday and submits the form. Nothing is submitted, published or charged until t
check_badgeCheck whether the SaaSCity badge is live on a site. Reads the given URL and, for a deep page, the site homepage too, rendering JavaScript if the static HTML misses it. A verified badge keeps a free listing booked before November 6, 2026 on a dofollow link. A paid listing needs no
get_submission_statusWhere a SaaSCity submission stands. By claim token: unclaimed, expired, claimed but the form not submitted yet, submitted and waiting for payment, submitted and in review, rejected, archived, or live. By slug: a live listing (launch week, badge, link type, points).
get_launch_weeksSaaSCity launch weeks: the next 12 Mondays. A round opens each Monday at 00:00 UTC, and a paid listing can take any of them.
get_offersSaaSCity listing offers with real prices - Basic listing and Premium listing - and exactly what each buys (dofollow link, city-map building, launch review). Every new listing is paid. Only a human can pay, on the claim page.
search_listingsSearch products listed on SaaSCity by keyword and/or category. Returns title, tagline, category, upvote points, the listing page and the product site. Useful for market research ("what else exists in this space?") before a launch.
get_listingOne live SaaSCity listing by slug: title, tagline, full description, category, upvote points, link type (dofollow/nofollow), listing page and product site.
get_leaderboardSaaSCity's most upvoted launches for this week's launch, the last 30 days, or all time, optionally within one category.
find_alternativesOther SaaSCity listings in the same category as a given listing, most upvoted first. Useful for competitor research and positioning.
calculate_arrTurn monthly recurring revenue into annual recurring revenue (ARR = MRR x 12), with ARPU when the customer count is given and the months to $100k, $1M and $10M ARR at a monthly growth rate. Count annual plans at their yearly price divided by 12 and leave one-time fees out of MRR.
calculate_arr_bridgeExplain how ARR moved over a period: ending ARR = starting ARR + new + expansion - contraction - churned. Returns net new ARR, growth, the SaaS quick ratio ((new + expansion) / (contraction + churned)), and net and gross revenue retention of the starting base. Full calculator: ht
calculate_churnCustomer churn and retention for a period, its monthly and annual equivalents (compounded, so 5% a month is about 46% a year, not 60%), and the average customer lifetime. Full calculator: https://saascity.io/free-tools/churn-rate-calculator
calculate_nrrNet revenue retention (NRR) and gross revenue retention (GRR) of a group of customers from their starting MRR, expansion, contraction and churned MRR, with annualised figures. Full calculator: https://saascity.io/free-tools/net-revenue-retention-calculator
rule_of_40Rule of 40 score (revenue growth % + profit margin %), plus the magic number, burn multiple and SaaS quick ratio when their inputs are given. Full calculator: https://saascity.io/free-tools/rule-of-40-calculator
calculate_npsNet Promoter Score from the counts of promoters (9-10), passives (7-8) and detractors (0-6), with the margin of error at 95% confidence. Full calculator: https://saascity.io/free-tools/nps-calculator
ab_test_significanceTwo-proportion test of an A/B result: conversion rates, relative uplift, p-value, confidence interval, the chance that B beats A, and a sample ratio mismatch check. Full calculator: https://saascity.io/free-tools/ab-test-calculator
markup_marginSelling price, profit and margin from a cost and a markup percent, or markup and margin from a cost and a selling price. Full calculator: https://saascity.io/free-tools/markup-calculator
uptime_downtimeAllowed downtime per day, week, month, quarter and year, in seconds, for an availability target such as 99.9%. Full calculator: https://saascity.io/free-tools/uptime-calculator
check_backlinkCheck whether a directory listing page links to your site and whether that link is followed. Reads the page's static HTML and reports every anchor pointing at your domain with its rel (nofollow, ugc, sponsored), hidden links, links that only go through the directory's own redirec
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 7일 점검
레지스트리 이름이 도메인 saascity.io 기준으로 확인되었어요(레지스트리가 도메인 소유를 확인해요)
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
476ms 만에 응답(HTTP 200)
로그인 필요 없음
도구 설명 23개를 읽었고, AI에게 보내는 숨겨진 지시는 없었어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 3개 중 3개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.
둘 다 가능해요. 내 컴퓨터에 설치해도 되고, 클라우드 버전에 연결해도 돼요.
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(2.1.0)은 오늘 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.
같은 카테고리에는: Spec Driven Development, Remote Desktop Commander, Qemu MCP
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Boot and drive QEMU VMs from an AI agent: keys, screenshots, serial. No guest agent.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
An MCP server for launching a product. Your AI agent can audit your homepage before launch, pick launch directories out of 1,600+ with Ahrefs DR, link type and price, and list the product on SaaSCity.
https://saascity.io/api/mcp (Streamable HTTP). No account, no API key.npx -y saascity-mcp for clients that only run local servers. It forwards to the hosted server.2026-07-28 (stateless) and the initialize-based versions 2025-11-25, 2025-06-18, 2025-03-26 and 2024-11-05, all on one endpoint.Built by SaaSCity, the launch directory for SaaS and AI tools. Full docs: saascity.io/mcp
Claude Code
claude mcp add --transport http saascity https://saascity.io/api/mcp
Claude Desktop, Cursor, Windsurf, VS Code and other clients with `mcpServers` JSON
{
"mcpServers": { "saascity": { "type": "http", "url": "https://saascity.io/api/mcp" } } }
Stdio-only clients
{
"mcpServers": { "saascity": { "command": "npx", "args": ["-y", "saascity-mcp"] } } }
It also runs straight from GitHub: npx -y github:nyyhao/saascity-mcp.
| Tool | What it does |
|---|---|
check_launch_readiness | Audits a homepage the way directory scrapers and link-preview bots see it: HTTPS, noindex, title, meta description, og:image (fetched to confirm it loads), X card, favicon, canonical, viewport, h1, JSON-LD, robots.txt, sitemap, parked or 404 pages, response time, and pages that are empty without JavaScript. Returns a 0-100 score, a verdict and a fix for each problem. |
recommend_launch_directories | Hand-picked directories for SaaS, AI or developer tools, grouped by when to submit. Each pick has a human-written verdict, including the ones not worth paying for. |
find_launch_directories | Filters the full dataset (1,600+ startup, SaaS and AI directories) by category, minimum DR, dofollow/nofollow, price and badge-swap requirement. Unverified fields come back as unknown instead of a guess. |
get_launch_directory | Looks up one directory by domain or URL before you pay for a listing. |
submit_project | Lists a product on SaaSCity as an inert draft and returns a claim link. Nothing is published or charged until a human opens it, and every listing is reviewed by a person. |
check_badge | Checks whether the SaaSCity badge is live on a site (a verified badge makes the listing link dofollow). |
get_submission_status | Where a submission stands, by claim token or listing slug. |
get_launch_weeks | Free slots left in the next 12 weekly launches. |
get_offers | Listing tiers and prices. |
search_listings | Searches products listed on SaaSCity by keyword and category. |
get_listing | One listing in full. |
get_leaderboard | Most upvoted launches this week, in the last 30 days, or all time. |
find_alternatives | Other listings in the same category as a given one. |
Every tool declares an outputSchema and returns structuredContent next to its text, plus readOnlyHint and the other behavior hints. Only submit_project writes anything, and it writes only a draft.
plan_launch (website_url, product_type): audit, fix the blockers, pick directories, produce a dated launch checklist.submit_to_saascity (website_url): draft a listing from the site, confirm it with you, then submit it.Check if https://example.com is ready to launch, then give me a two-week launch plan for an AI tool using free dofollow directories.
Is uneed.best worth it? What's its DR and is the link dofollow?
List my product on SaaSCity. The site is https://example.com.
drCheckedAt is the date of its last recheck, or null when the value comes from the last sweep of the list. Link type and price come from checks against the live sites, dated by dataUpdatedAt. Rows nobody has verified say unknown.submit_project 5 per day, check_launch_readiness 20 per hour, check_badge 30 per hour, everything else 30-60 per minute.submit_project is the only way a draft becomes a listing.curl -s https://saascity.io/api/mcp \
-H 'content-type: application/json' \ -H 'mcp-protocol-version: 2025-11-25' \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
MIT for this bridge. The directory data is served by saascity.io and is not part of this repository.