annotation-extractor 0.2.1

MCP server for extracting annotations and highlights from e-readers (Kobo, Kindle, and more)

annotation-extractor

MCP server for extracting annotations, highlights, and reading progress from e-readers.

Currently supports Kobo, with an extensible backend architecture for Kindle and others (coming soon)

Quick start

pip install annotation-extractor

# Or install from source
git clone https://github.com/rohitkaushik/annotation-extractor.git
cd annotation-extractor
pip install -e .

Usage

With Claude Code

claude mcp add annotations annotation-extractor

With Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "annotations": {
      "command": "annotation-extractor"
    }
  }
}

Manual

# Auto-detect mounted e-reader
annotation-extractor

# Or point to a specific Kobo database
KOBO_DB_PATH=/path/to/KoboReader.sqlite annotation-extractor

Tools

Tool	Description
list_books	List all books, optionally filtered to those with annotations
get_annotations	Get highlights and notes for a specific book (by title or ID)
search_annotations	Full-text search across all highlights and notes
get_reading_progress	Reading progress, time spent, and status for all books
get_book_details	Detailed metadata for a specific book

All tools accept optional backend_name (e.g., "kobo") and db_path parameters. When omitted, the server auto-detects connected devices.

Supported e-readers

Reader	Status	Data source
Kobo	Supported	.kobo/KoboReader.sqlite via USB
Kindle	Planned	My Clippings.txt via USB

Adding a new backend

1. Create src/annotation_extractor/backends/yourreader.py implementing EReaderBackend
2. Add your backend to _ALL_BACKENDS in registry.py
3. No changes needed to server.py or models.py

Development

git clone https://github.com/rohitkaushik/annotation-extractor.git
cd annotation-extractor
pip install -e ".[dev]"
pytest

License

MIT