Content Genie

content-genie-mcp

Korean-content-creator MCP that gives Claude live Naver/Daum/Google/YouTube/Zum trends, a 100+ Korean-holiday DB, and a viral-score predictor — so you stop tab-hopping between 5 trend dashboards before every post.

English · 한국어

---

Why content-genie?

Most "trend" MCPs are thin wrappers around Google Trends. If you're publishing for a Korean audience (Naver Blog, YouTube Korea, Instagram KR, TikTok), Google alone misses the signal — Naver Datalab, Daum search, Zum realtime, and KR-region YouTube each surface different keywords at different hours. content-genie consolidates all five sources into one MCP, layers a 100+ Korean-holiday + 14일-day-series + 절기 event database so Claude can plan around 빼빼로데이 and 수능 without being told, and finishes the loop with a viral-score predictor trained on the structural patterns (numbers, brackets, emotional triggers, urgency words) that move CTR in Korean content.

The Phase 4 refactor (v2.12.0, May 2026) made the whole thing safe to depend on: every scraper sits behind a per-source circuit breaker (3 fails → open 5 min) with a stale-cache fallback, so a Naver HTML change no longer takes the whole MCP down — it just degrades that one source and tells the LLM about it via resource://content-genie/sources.

What's new in v2.12.0

• 17 tools, one registry, six small files. The old 4,712-line index.ts is gone — tools live in src/tools/{trends,seo,contentIdeas,viralScoring,competitorAnalysis,koreanEvents}.ts. Adding a tool is a one-liner.
• Scrapers can't take the server down anymore. Per-source circuit breaker + LRU/TTL cache (15 min, 100 entries) + stale fallback. When Naver is degraded, Claude sees source_status: 'stale' and adapts.
• Two new MCP Resources for `@-mention`. resource://content-genie/korean-events/{year} returns the full event DB rebased to any year; resource://content-genie/sources exposes live breaker + cache state.
• Two MCP Prompts as guided workflows. viral-title chains optimize_title_hashtags → predict_viral_score → generate_ab_test_variants. competitor-analysis does URL analysis + gap-filling ideation.
• 38 tests across 8 suites. Circuit breaker transitions, cache eviction, scraper fallback paths, SSRF guard, every tool group — runs on Node 22 + 24 in CI.

5-minute Quickstart

# 1. Install via Claude Code (recommended)

claude mcp add content-genie -- npx -y content-genie-mcp

2. Or add to Claude Desktop's claude_desktop_config.json:

{

"mcpServers": { "content-genie": { "command": "npx", "args": ["-y", "content-genie-mcp"] } } }

1. Restart Claude Desktop (or claude will pick it up on the next run).
2. Try this in Claude:

오늘 한국에서 뜨는 키워드 5개로 유튜브 쇼츠 제목 후보 3개씩 만들고, 각각 바이럴 점수 등급 매겨줘.

1. Expected: Claude calls get_korean_trends (naver+daum+google+youtube+zum merged) → optimize_title_hashtags per keyword → predict_viral_score → returns a ranked S/A/B/C/D grade table with the structural reason ("제목에 숫자 + 호기심 트리거 포함").

Real use cases

1. "I need a Korean blog post topic that won't be obsolete by tomorrow"

Problem: Naver Blog rewards quick takes on the keywords trending *right now*, but those keywords change every 4 hours. With this MCP: Claude calls get_korean_trends({ platform: 'naver', limit: 20 }) and then generate_content_ideas against the freshest 5 keywords with seasonal: true. The seasonal layer adds upcoming Korean events from the 100+ DB — so the suggestion isn't just "AI 추천 도구" but "AI 추천 도구 + 수능 D-30 콘텐츠 기획" because get_seasonal_content_guide saw 수능 is 4 weeks out. Why it's better than the Naver Datalab UI: Datalab gives you a chart. This MCP gives you 5 titled, hashtag-optimized post drafts grounded in those same trends, in one conversational round-trip.

2. "Will this YouTube Shorts title actually pop?"

Problem: Title CTR is the single biggest lever on Shorts, but you only know after you publish. With this MCP: Paste your draft into Claude, say "use the viral-title prompt". The prompt chains optimize_title_hashtags → predict_viral_score → generate_ab_test_variants and returns an S~D grade plus 5 A/B variants with the structural deltas (added number, added urgency word, shortened to 25 chars). Why it's better than vibes: the scorer reads the same 6 signal classes a Korean copywriter would — emotional triggers (충격|실화|숨겨진), structural elements (numbers/brackets/?/!), urgency, social proof, utility framings (방법|꿀팁|노하우), and length window — and tells you which ones are missing.

3. "I run a small Korean brand, I need a content calendar that respects local holidays"

Problem: Generic calendar tools don't know about 빼빼로데이, 김장철, 수능, or 한가위 연휴, so you end up posting a promo on 현충일. With this MCP: Claude calls create_content_calendar({ months: 3, niche: 'beauty' }), which joins your 3-month window against the 100+ event DB (공휴일 18 + 데이 시리즈 12 + 절기 15 + 상업 이벤트 15 + 시즌/날씨 12 + 입시 10 + 쇼핑 10 + 크리에이터 특화 8) and produces a date-by-date plan with content themes per event. Why it's better than a Notion template: the DB is rebased to any year (resource://content-genie/korean-events/2027 is a single @-mention away), so the calendar stays accurate next year without you maintaining it.

Tools / Resources / Prompts

How it works

                    Claude (or any MCP client)

│ ▼ McpServer (SDK 1.25) │ ┌───────────┼───────────┐ ▼ ▼ ▼ 17 tools Resources Prompts │ ▼ runScraper() ◄── core/cache.ts (LRU + 15min TTL) │ ◄── core/circuitBreaker.ts (3-fail → open 5min) ▼ scrapers/{naver,daum,google,youtube,zum}.ts │ ▼ core/security.ts (SSRF + 30s timeout + 5MiB cap)

Three design choices that matter:

1. Per-source circuit breaker. A bad day at Naver doesn't take down 16 other tools — only the trend tools that need Naver, and even those return a stale-cache status: 'stale' envelope so the LLM can adapt.
2. Scrapers never throw. They return a ScrapeResult envelope (ok | stale | unavailable). All error handling is in one place (runScraper), so adding a new source is "write a scraper, return ScrapeResult, done".
3. Event DB rebased on read. The 100+ Korean holiday/event database is stored as month-day rules and rebased to any year on demand — so …/korean-events/2027 works today.

Configuration

HTTP endpoints (when MCP_HTTP_MODE=true):

Known limitations

• Scrapers are HTML-driven. Naver / Daum / Zum don't expose public trend APIs; the scrapers parse HTML. When they change their markup, the affected source returns status: 'unavailable' until we ship a parser fix. The circuit breaker keeps the rest of the MCP working in the meantime.
• Viral score is structural, not semantic. predict_viral_score is a heuristic over Korean copy patterns. It can't read the *meaning* of your post — only the structural / emotional / urgency signals in the title + description.
• No thumbnail image analysis. analyze_thumbnail works on a *thumbnail concept description*, not on an uploaded image. Image-in is on the roadmap.
• Korean-first. Hashtag templates, urgency words, and the event DB are Korean. English/JP modes are not in scope for v2.x.

When NOT to use this

• If you need a global trend dashboard, use Google Trends directly — content-genie is opinionated toward the Korean creator stack.
• If you need paid keyword data with search volume (네이버 검색광고 API, Ahrefs, SEMrush), use those — content-genie's SEO tools rely on free autocomplete + heuristic long-tail expansion.
• If you need deterministic LLM-free copy generation for compliance reasons, this MCP feeds an LLM — the LLM is what writes the actual titles.

Comparison

Roadmap

• More sources. Tistory realtime, Brunch picks, Kakao View — currently 5 sources, want 8.
• **Image-in