Your Apple Books library holds thousands of highlights — what you've underlined, what you've wondered, what you've finished and abandoned. Apple Books MCP is a reading copilot. It gives Claude direct access to your books, highlights, chapters, and reading progress. "Pick up where I left off — walk me back into last night's chapter" "Summarize my highlights from this week" "What am I in the middle of, and what's collecting dust?" Local-first. Open source. Made for readers.
Maker here. I built Apple Books MCP because I was tired of my reading being invisible to me.
I highlight a lot — nearly 9,000 passages across ~90 books. But those highlights live in the Apple Books app, and once you underline something, it essentially disappears. You can't ask "what have I been thinking about this week?" You can't pull up a quote you vaguely remember. You can't have a conversation about a book with anything that actually knows what caught your attention in it.
Claude + MCP changes that. This server exposes your whole Apple Books library — books, highlights, notes, reading progress, genres, and (new in v0.7.0) chapter text itself — so you can ask Claude real questions:
"Summarize what I've highlighted this week"
"What am I in the middle of reading, and what's collecting dust?"
"Pick up where I left off — walk me back into the chapter I was reading last night"
"Find everywhere in my library Dawkins wrote about kin selection"
The magic isn't any single query — it's that your reading becomes a surface you can talk to. Claude doesn't forget which books you've engaged with or what themes you circle.
A few things I care about:
Local-first: nothing leaves your machine. Your data stays in Apple Books' SQLite files, which this server reads (never writes).
Open source (Apache 2.0, GitHub)
Listed on MCP Registry and installable via uvx apple-books-mcp
What's next: PDF content access (it's EPUB-only for now), paragraph-level grounding for highlights (so quoted context snaps to paragraph boundaries instead of character windows), and a one-click "resume reading" prompt for whatever book is open.
Long-term I want this to feel like reading side-by-side with someone who's read every book on your shelf.
Would love to hear what questions you'd ask your library. Happy to answer anything about the architecture (MCP tools vs. resources vs. prompts was a fun design space) or the roadmap.
Apple Books MCP launched on Product Hunt on April 21st, 2026 and earned 74 upvotes and 4 comments, placing #37 on the daily leaderboard. Your Apple Books library holds thousands of highlights — what you've underlined, what you've wondered, what you've finished and abandoned. Apple Books MCP is a reading copilot. It gives Claude direct access to your books, highlights, chapters, and reading progress. "Pick up where I left off — walk me back into last night's chapter" "Summarize my highlights from this week" "What am I in the middle of, and what's collecting dust?" Local-first. Open source. Made for readers.
Apple Books MCP was featured in Productivity (650.7k followers), Open Source (68.4k followers), Artificial Intelligence (467.3k followers) and GitHub (41.2k followers) on Product Hunt. Together, these topics include over 250.7k products, making this a competitive space to launch in.
Who hunted Apple Books MCP?
Apple Books MCP was hunted by Vignesh Iyer. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Apple Books MCP stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Vignesh Iyer
Hey Product Hunt! 👋
Maker here. I built Apple Books MCP because I was tired of my reading being invisible to me.
I highlight a lot — nearly 9,000 passages across ~90 books. But those highlights live in the Apple Books app, and once you underline something, it essentially disappears. You can't ask "what have I been thinking about this week?" You can't pull up a quote you vaguely remember. You can't have a conversation about a book with anything that actually knows what caught your attention in it.
Claude + MCP changes that. This server exposes your whole Apple Books library — books, highlights, notes, reading progress, genres, and (new in v0.7.0) chapter text itself — so you can ask Claude real questions:
"Summarize what I've highlighted this week"
"What am I in the middle of reading, and what's collecting dust?"
"Pick up where I left off — walk me back into the chapter I was reading last night"
"Find everywhere in my library Dawkins wrote about kin selection"
The magic isn't any single query — it's that your reading becomes a surface you can talk to. Claude doesn't forget which books you've engaged with or what themes you circle.
A few things I care about:
Local-first: nothing leaves your machine. Your data stays in Apple Books' SQLite files, which this server reads (never writes).
Open source (Apache 2.0, GitHub)
Listed on MCP Registry and installable via uvx apple-books-mcp
What's next: PDF content access (it's EPUB-only for now), paragraph-level grounding for highlights (so quoted context snaps to paragraph boundaries instead of character windows), and a one-click "resume reading" prompt for whatever book is open.
Long-term I want this to feel like reading side-by-side with someone who's read every book on your shelf.
Would love to hear what questions you'd ask your library. Happy to answer anything about the architecture (MCP tools vs. resources vs. prompts was a fun design space) or the roadmap.
Thanks for checking it out 📚
— Vignesh