notebooklm-skill MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Four-phase pipeline: Collect → Research → Generate → Publish
NotebookLM produces citation-backed research answers
Also pulls NotebookLM artifacts: audio overviews, slides, quizzes, flashcards
Dual deployment: Claude Code skill or MCP server (works with Cursor, Gemini CLI)
Browser-based Google OAuth — no API keys to manage
Python 3.10+ required; wraps the notebooklm-py library

라이브 데모

실제 사용 모습

notebooklm-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "notebooklm-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/claude-world/notebooklm-skill",
        "~/.claude/skills/notebooklm-skill"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "notebooklm-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/claude-world/notebooklm-skill",
        "~/.claude/skills/notebooklm-skill"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "notebooklm-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/claude-world/notebooklm-skill",
        "~/.claude/skills/notebooklm-skill"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "notebooklm-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/claude-world/notebooklm-skill",
        "~/.claude/skills/notebooklm-skill"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "notebooklm-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/claude-world/notebooklm-skill",
        "~/.claude/skills/notebooklm-skill"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "notebooklm-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/claude-world/notebooklm-skill",
          "~/.claude/skills/notebooklm-skill"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add notebooklm-skill -- git clone https://github.com/claude-world/notebooklm-skill ~/.claude/skills/notebooklm-skill

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: notebooklm-skill

How to turn a stack of sources into a researched, cited article

👤 Content marketers and technical writers publishing researched longform ⏱ ~45 min intermediate

언제 쓸까: You have 5-20 URLs and PDFs on a topic and need a polished article with citations in under an hour.

사전 조건

Python 3.10+ — pyenv install 3.10 or system python3
Google account with NotebookLM access — Sign in at notebooklm.google.com once; browser session is reused
notebooklm-py library — pip install notebooklm-py

흐름

Collect sources into a notebook

Create a notebook titled 'CRDT-landscape-2026' and add these 8 URLs and this PDF.✓ 복사됨

→ Notebook ID returned; source count confirmed
Run research queries

Ask the notebook: 'What are the main CRDT types and their tradeoffs? Cite each claim.'✓ 복사됨

→ Structured answer with inline citations to specific sources
Generate an article

Using those findings, draft a 1500-word article for a backend audience. Keep citations as footnotes.✓ 복사됨

→ Draft with [n] citation markers keyed to source URLs
Publish

Save to drafts/crdt-landscape.md with frontmatter (title, date, tags).✓ 복사됨

→ Markdown file on disk

결과: A cited, publishable draft grounded in specific sources — not hallucinated.

함정

Browser auth expires silently — Re-open notebooklm.google.com and refresh; skill reuses the cookie jar
Claude paraphrases a claim without its citation — Explicitly instruct: 'Every factual sentence must end with its [n] citation.'

함께 쓰기: smart-illustrator-skill

Turn research sources into a podcast-style audio overview

👤 Podcasters and educators who want an audio summary from reading material ⏱ ~15 min beginner

언제 쓸까: You want NotebookLM's Audio Overview feature triggered from your agent instead of the web UI.

흐름

Add sources and request audio

Create notebook from these 6 papers, then trigger audio overview.✓ 복사됨

→ Audio generation kicked off; status returned
Poll and download

Wait for audio, then save as overview.mp3 in my downloads.✓ 복사됨

→ Local MP3 file

결과: A downloaded audio overview without opening the NotebookLM web UI.

함정

Audio takes 2-5 minutes to render — Use the polling flow; don't expect sync completion

조합

다른 MCP와 조합해 10배 효율

notebooklm-skill + smart-illustrator-skill

NotebookLM research → Claude drafts → Smart Illustrator adds diagrams

Research 'vector DB landscape' with notebooklm, draft a 2000-word article, illustrate with smart-illustrator.✓ 복사됨

notebooklm-skill + ai-marketing-claude-code-skill

Turn researched content into marketing campaigns with real citations

Take findings from notebook XYZ and run the go-to-market skill to produce a launch plan with cited claims.✓ 복사됨

notebooklm-skill + claude-skills-journalism-skill

Journalism workflows that demand source verification

Use notebooklm to verify each claim in this draft against the uploaded primary sources before publishing.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
create_notebook	title: str, sources: list[url\|pdf\|youtube]	First step of any research task	NotebookLM free quota
add_sources	notebook_id, sources	Extend existing notebook	free
ask	notebook_id, question	Primary research interaction	NotebookLM free quota
generate_audio_overview	notebook_id, style?	When you want the podcast-style overview	free, async
export_artifacts	notebook_id, type: 'slides'\|'report'\|'quiz'\|'flashcards'	Repurposing research into other formats	free

비용 및 제한

운영 비용

API 쿼터: NotebookLM free tier is generous but unpublished. Heavy use may trigger rate limiting.
호출당 토큰: Research answers use Google's quota; Claude token use depends on drafting length
금액: Free with a Google account
팁: Batch multiple questions per notebook session — avoid re-uploading sources across notebooks.

보안

권한, 시크릿, 파급범위

자격 증명 저장: Browser cookie session for Google. No API keys. Session stored in notebooklm-py's local cache.

데이터 외부 송신: All source content is uploaded to NotebookLM (Google). Don't feed confidential material.

Sources are processed by Google's servers — review Google's NotebookLM terms before feeding proprietary content.
Session cookie grants broad Google account read where NotebookLM has access. Use a dedicated Google account for automation if possible.

문제 해결

자주 발생하는 오류와 해결

Auth failed / 'please sign in'

Open notebooklm.google.com in your default browser, sign in, then retry. Skill reuses the browser cookie jar.

확인: python -c 'import notebooklm_py; print(notebooklm_py.whoami())'

Source rejected as unsupported

NotebookLM accepts specific formats. Convert PDFs to text or host as public URL if needed.

Audio overview stuck in 'pending'

Normal — takes 2-5 min. Poll with export status.

대안

notebooklm-skill 다른 것과 비교

대안	언제 쓰나	단점/장점
Manual web-search + summarize	You don't have a Google account or need air-gapped workflow	No citation grounding; higher hallucination risk
Perplexity API	You want a paid API with SLAs	Costs money, but more reliable than browser automation

notebooklm-skill