ebook-mcp MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

ebook.replay ▶ prêt

0/0

Installer

Choisissez votre client

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

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

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

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

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

claude mcp add ebook -- uvx ebook-mcp

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : ebook-mcp

Find and quote a passage you vaguely remember

👤 Readers / researchers ⏱ ~5 min beginner

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

Prérequis

The book file on disk — EPUB or PDF

Déroulement

Load TOC

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

→ TOC + best-guess chapter
Pull the chapter

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

→ Quoted passage

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

Pièges

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

Quand l'utiliser : You want to decide whether to actually read a book, or need a refresher after finishing.

Déroulement

TOC first

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

→ Outline
Per-chapter summary

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

→ Complete book digest

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

Pièges

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

Combiner avec : filesystem

Audit your ebook library's metadata

👤 Calibre users, ebook hoarders ⏱ ~15 min beginner

Quand l'utiliser : Your library has 500 ebooks and you want to find ones with missing title/author metadata.

Déroulement

Scan

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

→ Incomplete-metadata list

Résultat : Quick metadata hygiene pass.

Combiner avec : filesystem

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

ebook + local-rag

Build a searchable library index

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

ebook + notion

Auto-populate your reading journal

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
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

Coût et limites

Coût d'exécution

Quota d'API: None
Tokens par appel: Chapters 2k-30k tokens depending on length
Monétaire: Free (Apache 2.0)
Astuce: Always load TOC first. Then load chapters one at a time rather than the whole book.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : None — local files only

Sortie de données : 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.

Dépannage

Erreurs courantes et correctifs

Unable to parse PDF

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

Vérifier : 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.

Alternatives

ebook-mcp vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills