ebook-mcp MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

EPUB: metadata, TOC, chapter content, batch processing
PDF: metadata, TOC, page/chapter extraction, Markdown output
Batch ops across a folder of books
Python-based, install via uv pip install -e .
Apache 2.0

라이브 데모

실제 사용 모습

ebook.replay ▶ 준비됨

0/0

설치

클라이언트 선택

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

{
  "mcpServers": {
    "ebook": {
      "command": "uvx",
      "args": [
        "ebook-mcp"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "ebook": {
      "command": "uvx",
      "args": [
        "ebook-mcp"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "ebook": {
      "command": "uvx",
      "args": [
        "ebook-mcp"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ebook": {
      "command": "uvx",
      "args": [
        "ebook-mcp"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "ebook",
      "command": "uvx",
      "args": [
        "ebook-mcp"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "ebook": {
      "command": {
        "path": "uvx",
        "args": [
          "ebook-mcp"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add ebook -- uvx ebook-mcp

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

사용 사례

실전 활용법: ebook-mcp

Find and quote a passage you vaguely remember

👤 Readers / researchers ⏱ ~5 min beginner

언제 쓸까: 'There was something in that book about X...' — you need the exact quote and can't be bothered to flip pages.

사전 조건

The book file on disk — EPUB or PDF

흐름

Load TOC

Show me the TOC of ~/Books/deep-work.epub. Which chapter likely discusses shallow work vs deep work?✓ 복사됨

→ TOC + best-guess chapter
Pull the chapter

Get the text of chapter 3. Find the passage about shallow-work-as-default.✓ 복사됨

→ Quoted passage

결과: Quote in hand, citable, in 2 minutes.

함정

Scanned PDFs have no text layer — Run OCR first

Generate a chapter-by-chapter summary of a technical book

👤 Engineers learning from a book on their TBR ⏱ ~30 min intermediate

언제 쓸까: You want to decide whether to actually read a book, or need a refresher after finishing.

흐름

TOC first

Load TOC of book.pdf. Show me chapter titles and approximate page ranges.✓ 복사됨

→ Outline
Per-chapter summary

For each chapter, load its content and produce a 3-bullet summary. Output as a single Markdown doc.✓ 복사됨

→ Complete book digest

결과: A 1-2 page book digest you can share or revisit.

함정

Huge books blow the token budget if you load all chapters at once — Process one chapter at a time; write intermediate summaries to disk

함께 쓰기: filesystem

Audit your ebook library's metadata

👤 Calibre users, ebook hoarders ⏱ ~15 min beginner

언제 쓸까: Your library has 500 ebooks and you want to find ones with missing title/author metadata.

흐름

Scan

For each .epub under ~/Books, get metadata. List any where title or author is missing or contains 'Unknown'.✓ 복사됨

→ Incomplete-metadata list

결과: Quick metadata hygiene pass.

함께 쓰기: filesystem

조합

다른 MCP와 조합해 10배 효율

ebook + local-rag

Build a searchable library index

For each book, get_chapter by chapter, ingest into local-rag with book title as source.✓ 복사됨

ebook + notion

Auto-populate your reading journal

Take this just-finished book; summarize each chapter; create a Notion page in 'Books Read'.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
get_metadata	path: str	First pass on any book	free
get_toc	path: str	Before pulling chapter content	free
get_chapter	path, chapter_id or id_range	Load a specific chapter	free
get_pages	path, from_page, to_page (PDF only)	Page-range extraction for PDFs	free

비용 및 제한

운영 비용

API 쿼터: None
호출당 토큰: Chapters 2k-30k tokens depending on length
금액: Free (Apache 2.0)
팁: Always load TOC first. Then load chapters one at a time rather than the whole book.

보안

권한, 시크릿, 파급범위

자격 증명 저장: None — local files only

데이터 외부 송신: Book content goes to your LLM provider

Respect copyright — this tool lets you query your own books; don't republish.
DRM-protected files will not parse; remove DRM only where legally permitted in your jurisdiction.

문제 해결

자주 발생하는 오류와 해결

Unable to parse PDF

Scanned/image-only PDF has no text layer. Run ocrmypdf first.

확인: pdftotext input.pdf - | head

EPUB chapter ID not found

IDs come from the TOC exactly. Call get_toc first.

Large PDF makes get_chapter timeout

Use get_pages with a smaller page range; batch.

대안

ebook-mcp 다른 것과 비교

대안	언제 쓰나	단점/장점
Calibre + custom script	You want full Calibre integration	More setup; no MCP wrapper
pdfplumber / pymupdf directly	You build your own tooling	Build your own MCP wrapper

ebook-mcp