Ebook MCP

An MCP server that enables AI agents to interact with EPUB and PDF ebooks through natural language. Exposes tools for extracting metadata, table of contents, and chapter/page content in Markdown format from both EPUB and PDF files. Supports batch processing of multiple files and provides structured access to book content for summarization, quizzing, and interactive reading.

Evaluated Mar 06, 2026 (0d ago) vunknown
Homepage ↗ Repo ↗ Other mcp epub pdf ebook document-extraction markdown reading library-management
⚙ Agent Friendliness
60
/ 100
Can an agent use this?
🔒 Security
66
/ 100
Is it safe for agents?
⚡ Reliability
59
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
62
Documentation
60
Error Messages
45
Auth Simplicity
70
Rate Limits
50

🔒 Security

TLS Enforcement
80
Auth Strength
70
Scope Granularity
55
Dep. Hygiene
65
Secret Handling
60

Community/specialized tool. Apply standard security practices for category. Review documentation for specific security requirements.

⚡ Reliability

Uptime/SLA
65
Version Stability
60
Breaking Changes
55
Error Recovery
55
AF Security Reliability

Best When

You have a collection of EPUB or PDF ebooks and want to interact with their content through an AI assistant for reading, studying, or content extraction.

Avoid When

Your PDFs lack tables of contents, your ebooks are DRM-protected, or you need to process very large documents without pagination strategies.

Use Cases

  • • Having AI summarize or discuss specific chapters of an ebook
  • • Building AI-powered study tools that quiz you on book content
  • • Extracting and converting ebook content to Markdown for downstream processing
  • • Managing and searching across a personal ebook library via AI
  • • Interactive reading sessions where you ask questions about book content

Not For

  • • DRM-protected ebooks (no DRM stripping capability)
  • • PDFs without a table of contents (chapter navigation limited without TOC)
  • • Very large PDFs without pagination (should use page ranges to avoid memory issues)
  • • Non-book document types (Word, HTML, etc.)
  • • Audio book formats

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication required. Runs locally. User IDs used for organizational purposes only, not access control.

Pricing

Model: open_source
Free tier: Yes
Requires CC: No

Apache-2.0 licensed. Fully free and open source.

Agent Metadata

Pagination
offset
Idempotent
Full
Retry Guidance
Not documented

Known Gotchas

  • ⚠ PDF features require a table of contents in the document for chapter navigation
  • ⚠ Large PDF processing should use page ranges to avoid memory issues
  • ⚠ Requires uv (Python package manager) for installation and running
  • ⚠ Built on fastmcp framework - depends on its stability
  • ⚠ No DRM support - will fail silently or error on protected content
  • ⚠ Chapter IDs for EPUB must be discovered via get_toc before accessing content

Alternatives

Claude's built-in PDF reading LlamaIndex document loaders Unstructured.io marker (PDF to Markdown) manual text extraction

Full Evaluation Report

Detailed scoring breakdown, competitive positioning, security analysis, and improvement recommendations for Ebook MCP.

$99
API endpoint ↗ Agent guide ↗ Report inaccuracy

Scores are editorial opinions as of 2026-03-06.

5178
Packages Evaluated
26151
Need Evaluation
173
Need Re-evaluation
♥
Community Powered