agentleFS
vladmdgolamvladmdgolam/agent-skills/skills/apple-books-mcp/SKILL.md

apple-books-mcp

Skill9 starsChanged 33 days agoMITView on GitHub

Extracts highlights, annotations, and book data from Apple Books via MCP. Use when: user asks to export book highlights, extract annotations with colors, search highlights across books, create highlight summaries, or match books from a reading list against their Apple Books library. Covers efficient batch color extraction (5 calls instead of 150+), annotation-to-book matching, and markdown export patterns.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Solution: Call get_highlights_by_color once per color (5 total calls), then cross-reference annotation IDs programmatically.

    line 37
  2. Very specific:

    Call list_all_books and match against user's list.

    line 75
  3. Distinctive:

    Use partial/fuzzy matching — "Vignelli Canon" may appear as just "canon"

    line 78
  4. Distinctive:

    Read the user's list (file, note, etc.) to get book titles

    line 152
  5. Very specific:

    If color needed: describe_annotation(annotation_id=ID) for the few results

    line 163

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Apple Books MCP

MCP server: vgnshiyer/apple-books-mcp

Install: npx -y @anthropic-ai/claude-code mcp add apple-books -- uvx apple-books-mcp

Tools Reference

ToolPurpose
list_all_booksList all books (ID, title, author)
get_book_annotationsAll annotations for a book by ID. No color data.
describe_annotationFull details for one annotation including color
get_highlights_by_colorAll highlights of one color across entire library
search_highlighted_textSearch annotations by highlighted text
search_notesSearch by user-written notes
list_all_annotationsAll annotations across all books
list_all_collectionsList collections
get_collection_booksBooks in a collection
describe_book / describe_collectionDetails by ID
recent_annotationsRecently created annotations
full_text_searchFull text search across books

Critical: Color Extraction Strategy

get_book_annotations does NOT return colors. describe_annotation returns colors but one at a time — 150+ calls for a single book.

Solution: Call get_highlights_by_color once per color (5 total calls), then cross-reference annotation IDs programmatically.

Available colors: PINK, BLUE, YELLOW, GREEN, PURPLE
Underlines: color = null, is_underline = 1

Build the Color Map

import json, glob

# After calling get_highlights_by_color for PINK, BLUE, YELLOW, GREEN, PURPLE
# Results save to files when they exceed token limits

ann_color = {}
colors = ["PINK", "BLUE", "YELLOW", "GREEN", "PURPLE"]

for color_file, color in zip(sorted(glob.glob("path/to/results/*.txt")), colors):
    with open(color_file, 'r') as f:
        data = json.load(f)
    current_id = None
    for line in data.get("text", "").split("\n"):
        line = line.strip()
        if line.startswith("ID: "):
            current_id = line.split("ID: ")[1].strip()
        elif line.startswith("Selected text: ") and current_id:
            selected = line[len("Selected text: "):]
            if selected and selected != "None":
                ann_color[current_id] = color

# Look up: ann_color.get(str(annotation_id), None)  # None = underline

Workflow: Extract Highlights for a Book List

Step 1: Match Books

Call list_all_books and match against user's list. Tips:

  • Books may appear under translated titles (e.g., Russian editions)
  • PDFs often have garbled or filename-based titles
  • Use partial/fuzzy matching — "Vignelli Canon" may appear as just "canon"
  • Same book may exist in multiple editions (different IDs)

Step 2: Get Annotations per Book

get_book_annotations(book_id="531")

Returns: ID, selected_text, representative_text, note, chapter, location, modification date. Filter out entries where selected_text is None (empty bookmarks).

Step 3: Get Colors (Batch)

get_highlights_by_color(color="PINK")
get_highlights_by_color(color="BLUE")
get_highlights_by_color(color="YELLOW")
get_highlights_by_color(color="GREEN")
get_highlights_by_color(color="PURPLE")

Results are large (100k-400k chars). Use Python to parse.

Step 4: Export to Markdown

color_emoji = {
    "PINK": "🩷", "BLUE": "🔵", "YELLOW": "🟡",
    "GREEN": "🟢", "PURPLE": "🟣",
}

lines = [f"# {title}", f"**{author}**", "", "---", ""]
for ann_id, text in annotations:
    color = ann_color.get(str(ann_id), None)
    tag = color_emoji.get(color, "〰️")  # 〰️ for underlines
    lines.append(f"{tag} {text}")
    lines.append("")

Annotation Data Structure

From describe_annotation:

{
  "id": 2133,
  "selected_text": "be impeccable with your word",
  "representative_text": "The first agreement is to be impeccable...",
  "note": null,
  "is_underline": 0,
  "style": 4,
  "color": "PINK",
  "chapter": null,
  "location": "epubcfi(/6/12[c005]!/4/10,/1:26,/2/1:28)"
}

Style-to-Color Mapping

StyleColor
0Underline (no color)
1Green
2Blue
3Yellow
4Pink
5Purple

Examples

Example 1: Export All Highlights from a Reading List

User says: "Extract highlights from the books in my reading list"

  1. Read the user's list (file, note, etc.) to get book titles
  2. list_all_books → match titles to IDs
  3. For each matched book: get_book_annotations(book_id=ID) → collect annotation IDs + text
  4. get_highlights_by_color x5 → build color map
  5. Python script combines annotations + colors → writes .md files per book

Example 2: Search for a Quote Across All Books

User says: "Find where I highlighted something about shadow work"

  1. search_highlighted_text(text="shadow") → returns matching annotations with book context
  2. If color needed: describe_annotation(annotation_id=ID) for the few results

Example 3: Get All Pink Highlights

User says: "Show me all my pink highlights"

  1. get_highlights_by_color(color="PINK") → all pink highlights across library
  2. Group by book title for readability

Troubleshooting

SymptomCauseFix
list_all_books emptyApple Books never openedOpen Apple Books app once
No annotations for a bookBook was read but not highlightedExpected behavior
describe_annotation color is nullIt's an underlineCheck is_underline field
Color results too largeMany highlights in libraryResults auto-save to file; parse with Python
Book title doesn't matchDifferent edition/translationTry author name or partial title
selected_text is NoneBookmark, not a highlightFilter these out

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.