annotation-extractor

MCP server for extracting annotations, highlights, and reading progress from e-readers. Supports Kobo, Kindle, and Boox.

mcp tools agents github

Install

pip install annotation-extractor

Or from source:

git clone https://github.com/rkaushik29/annotation-extractor-mcp.git
cd annotation-extractor
pip install -e .

Usage

Connect your e-reader via USB, add the MCP server to your agent, and start asking questions about your reading.

Client	Setup
Claude Code	`claude mcp add annotations -- annotation-extractor`
Claude Desktop	Add to `claude_desktop_config.json`
OpenClaw	`openclaw mcp add annotations -- annotation-extractor`
Gemini CLI	Add to `~/.gemini/settings.json`
Codex	`codex --mcp-config mcp.json`

For JSON config clients, use:

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

Try it out

Once the MCP is connected and your e-reader is plugged in, try asking your agent:

"What are my highlights from the last book I read?"

"Search my annotations for anything about consciousness"

"Show me all the notes I took while reading Neuromancer"

Supported E-Readers

Reader	Data Source
Kobo	`.kobo/KoboReader.sqlite` via USB
Kindle	`My Clippings.txt` via USB
Boox	Annotation export directory (one `.txt` per book) via USB

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", "kindle", "boox") and db_path parameters. When omitted, the server auto-detects connected devices.

Environment Variables

If auto-detection doesn't find your device, point to the data source directly:

Variable	Backend
`KOBO_DB_PATH`	Kobo
`KINDLE_CLIPPINGS_PATH`	Kindle
`BOOX_EXPORT_PATH`	Boox

Development

git clone https://github.com/rkaushik29/annotation-extractor-mcp.git
cd annotation-extractor
pip install -e ".[dev]"
pytest

The project uses a pluggable backend architecture. To add a new e-reader, implement the EReaderBackend abstract class and register it in registry.py.