Readwise MCP. Access your knowledge base with natural conversation.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Readwise MCP Server connects your AI client directly to your entire reading library. Manage books, highlights, tags, and spaced repetition reviews using natural language commands.
Your agent can search specific passages, create new notes, or pull up your daily review queue—all without you opening the Readwise app.
What your AI agents can do
Check readwise status
Verifies that your API connection to Readwise is active and working.
Create highlight
Adds a new highlight directly into a specified book.
Delete highlight
Removes an existing, unwanted highlight from your library.
The agent retrieves book metadata by searching titles, filtering by category, or listing all saved books.
You can create new highlights, update existing ones, or delete old notes directly through conversation.
The server pulls your daily spaced repetition review queue and allows you to retrieve specific passages for study.
You can list all existing tags or search highlights based on their associated tags.
The agent exports your highlight data incrementally, allowing you to pull historical data for backup or analysis.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Readwise MCP Server: 16 Tools for Reading Management
Use these tools with your agent to interact with every aspect of your reading library—from searching specific passages to managing full books and reviews.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Readwise on Vinkius019dd148check readwise status
Verifies that your API connection to Readwise is active and working.
019dd148create highlight
Adds a new highlight directly into a specified book.
019dd148delete highlight
Removes an existing, unwanted highlight from your library.
019dd148export highlights
Downloads all highlights. It supports incremental exports so you only pull new data since a specific date.
019dd148get book
Retrieves core information about a specific book by title or ID.
019dd148get daily review
Fetches the current set of spaced repetition reviews you need to study today.
019dd148get highlight
Retrieves all details for a single, specific highlight using its ID.
019dd148list books
Outputs a list of every book currently stored in your Readwise library.
019dd148list books by category
Lists only the books you've saved that fall under a specific category.
019dd148list books by source
Lists all books grouped by their original source (e.g., Kindle, PDF).
019dd148list highlights
Returns a list of highlights, showing the text, note, location, and associated tags.
019dd148list reviews
Shows you what's waiting in your review queue without fetching the actual content yet.
019dd148list tags
Retrieves a complete list of all tags you have assigned across your notes and highlights.
019dd148search books
Searches your entire book collection by keyword or title.
019dd148search highlights
Finds specific passages or notes based on keywords, allowing you to quickly locate ideas.
019dd148update highlight
Modifies the text, note, or tags of an existing highlight after it was created.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Readwise, then connect any of our 4,900+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,900+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Readwise. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 16 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Sifting through notes and highlights feels like a scavenger hunt.
Right now, when you find a key idea—say, how to improve your startup's marketing funnel—you have to remember exactly where it came from. You open the Readwise site, click into 'Notes,' then use the search bar, maybe narrowing by tag or source. It takes three clicks and several seconds of mental effort just to confirm if you already captured that thought.
With the Readwise MCP Server, you tell your agent: 'Find me all notes about funnel optimization.' The server runs `search_highlights` instantly. Your AI client returns a curated list of passages directly in your chat window—no clicking required.
Readwise MCP Server: Use the Readwise tools to manage reading data.
You don't have to manually run export jobs or check which notes are missing. The agent handles complex operations like fetching your daily review queue (`get_daily_review`) and compiling a full list of all your available tags (`list_tags`) in one go.
It means the server treats your entire library as an API endpoint. You just ask for the data you need, and it shows up.
What you can do with this MCP connector
Readwise MCP Server connects your AI client straight into your whole reading life, period. You don't gotta dig through the Readwise app; you just tell your agent what you need, and it gets it from your data. It's like having a personal librarian who lives inside your chat window.
Want to know which books you've read? Your agent uses list_books to give you a rundown of everything in your library. You can narrow that down by asking for books saved under a specific category using list_books_by_category, or see all the material grouped by where it came from—like Kindle versus PDF—with list_books_by_source.
If you're looking for something specific, just hit it with a title or keyword, and the agent uses search_books to pull up the relevant books. Need the basic info on one book? get_book grabs all that metadata by ID or title.
Managing your actual notes is where this thing gets serious. If you read something killer, you can use create_highlight to drop a new highlight into any specific book immediately. Did you change your mind about a note? No sweat; update_highlight lets you modify the text, tags, or whole damn note after it's already there.
And if that highlight was garbage and you wanna trash it? Use delete_highlight. To pull up details on one single piece of genius writing, use get_highlight with its ID. You can see everything you’ve captured by running list_highlights, which spits out the text, your note, location, and tags for every highlight.
Want to find a specific thought or passage? Just run search_highlights; it finds passages based on keywords or associated tags.
You gotta organize that stuff, right? Your agent can pull up a complete list of every single tag you've used across all your notes using list_tags. It’s how you keep the signal from the noise. When you need to study, forget opening the app. The server uses get_daily_review to fetch exactly what spaced repetition review material you gotta hit today.
If you just wanna see what reviews are waiting without studying them right now, run list_reviews.
Need to export your data for backups or analysis? You can use export_highlights. This tool is smart; it supports incremental exports so you only pull new data since a specific date, which saves time and bandwidth. To make sure everything's connected, just ask the agent to run check_readwise_status to verify your API connection is up and running.
Listen up: if you need to work with any of these tools—from listing all books (list_books) or grabbing book details (get_book), to managing notes by creating, updating, or deleting highlights using create_highlight, update_highlight, and delete_highlight—your agent handles the entire process. It's direct, it's fast, and you don't gotta think about which button to push.
019dd148-5508-7185-8f86-4b057d3c72f8 
How Readwise MCP Works
- 1 Subscribe to the server and input your Readwise API Token.
- 2 Your AI client uses a natural language prompt (e.g., 'Find all highlights on stoicism').
- 3 The MCP Server maps the request to the appropriate tool (like
search_highlights) and returns structured data to your agent.
The bottom line is: you talk to your reading notes, and your AI client runs the commands for you.
Who Is Readwise MCP For?
This is for researchers, students, writers, or anyone who collects knowledge from books. If you're tired of opening 15 tabs just to find a quote or review an old concept, this saves you time. It lets you treat your entire reading library like a searchable database.
Uses the agent to pull highlights related to specific theories across dozens of sources, then summarizes those findings for a paper.
Asks the server for 'all my quotes about leverage' and feeds that list into an article draft without switching contexts.
Runs get_daily_review to immediately test recall on material from months ago, making sure the knowledge sticks.
What Changes When You Connect
- Find quotes instantly: Instead of manually scrolling, use
search_highlightsto pull every passage mentioning 'stoicism' across all your source material. You get the data in seconds. - Keep track of sources: Use
list_books_by_sourceorlist_books_by_categoryto see exactly where a concept came from, keeping your knowledge organized by origin. - Study efficiently: The agent runs
get_daily_reviewto pull today's spaced repetition cards. You study the material without ever seeing the underlying database structure. - Organize on the fly: Use
list_tagsand thencreate_highlighttogether. When you find a key insight, you can highlight it and assign a tag like 'Finance Theory' immediately. - Build a data archive: If you need to analyze your notes for tax purposes or grant writing, use
export_highlights. It supports incremental exports, so you don't re-download everything every time.
Real-World Use Cases
Drafting an academic paper on behavioral economics.
Problem: You need to synthesize three different concepts—loss aversion, sunk cost fallacy, and cognitive bias—from books saved over the last year. Agent Action: Your agent runs search_highlights using those keywords, gathers all relevant passages, and compiles them into a coherent summary for you.
Quickly checking if an idea is already noted.
Problem: You read something useful but aren't sure if you highlighted it before. Agent Action: You ask the agent to 'search my highlights about AI ethics.' The tool runs search_highlights and tells you exactly what you wrote, saving you from rereading.
Curating a reading list for a client.
Problem: A client needs books on deep work but only from specific sources. Agent Action: You ask the agent to list_books_by_source and then filter that result by category, providing them with an immediate, actionable bibliography.
Preparing for a big exam or interview.
Problem: You need to prove you retained information from six months ago. Agent Action: The agent triggers get_daily_review and presents the flashcard-style material, forcing retrieval practice on difficult concepts.
The Tradeoffs
Trying to search by vague concept.
Prompting 'Tell me everything I read that was good.' This is too broad and the server can't interpret intent without more detail, resulting in a useless list of books.
→
Instead, specify your action. Use list_books to see categories first, then ask the agent to run search_highlights using specific keywords like 'dichotomy of control' or 'negative visualization'.
Updating a highlight manually in the UI.
Spending time clicking into Readwise, finding the note, and then editing it. This is slow and context-switching kills flow.
→
Use update_highlight. Just tell your agent: 'Update my highlight from 'Meditations' with this new summary.' It changes it for you instantly.
Assuming the data export includes everything.
Expecting a simple download that contains notes from all sources and tags. The raw data might be incomplete or outdated.
→
Use export_highlights with an updatedAfter filter. This guarantees you only pull highlights since your last backup, ensuring you get the latest version of your knowledge.
When It Fits, When It Doesn't
Use this server if your workflow is centered on retrieving or manipulating existing notes and highlights from a large, diverse corpus of reading material. The core strength here is that your agent can perform deep data lookups (search_highlights) across all sources without you needing to open the Readwise web client. Don't use it if you just need to manage book metadata—use list_books or get_book. You also shouldn't rely on it for real-time, live collaboration; this is a static knowledge repository. If your goal is building complex agent workflows that require constant data ingestion from external sources (like CRM or email), you might need an alternative server type instead.
Common Questions About Readwise MCP
How do I find all my highlights related to a certain topic using search_highlights? +
You simply prompt your agent with the query. The tool runs search_highlights and returns passages matching those keywords, like 'sustainability' or 'quantum physics'. It doesn't just list notes; it pulls specific text snippets.
Can I use create_highlight to add a note if the book isn't fully linked? +
Yes. You can use create_highlight by providing the necessary Book ID and the content/note, even if you feel the link is incomplete. The tool requires specific identifiers to attach the new data correctly.
What's the difference between list_books and search_books? +
list_books provides every book ID and title in your library, regardless of what you are searching for. search_books actively searches by keyword or title to help you locate a specific volume faster.
Do I need to manually run export_highlights after using the server? +
No. The agent handles running export_highlights for you when prompted, particularly supporting incremental exports so you only download data updated since your last successful pull.
How does get_daily_review work in practice? +
You prompt the agent to 'start my review session.' It then calls get_daily_review, which pulls all current spaced repetition cards, presenting them for immediate study.
What do I need to provide when running check_readwise_status? +
You must supply a valid Readwise API Token. This token, found in your account settings, proves the connection and allows your agent to manage your data. Running this tool confirms if the server can talk to your personal library.
How do I find out what tags are available using list_tags? +
The list_tags tool returns a complete inventory of every tag currently applied across your entire Readwise library. This lets you see the full scope of your knowledge structure before creating new annotations or reports.
If I need to back up my data, how does export_highlights handle large volumes? +
It supports incremental exporting using an updatedAfter filter. This means you don't download everything every time; instead, the tool pulls only highlights that have been updated since a specific date, keeping your backup process fast and efficient.
What can I do with the Readwise connector? +
You can list, search, create, update, and delete highlights, browse books by source or category, manage tags, access your daily spaced repetition review, and export all data incrementally for analysis or backup.
How does the daily review feature work? +
The daily review tool retrieves highlights selected by Readwise's spaced repetition algorithm, helping your AI agent surface the most important passages at the optimal retention interval.
Can I filter books by where they came from? +
Yes, you can filter by source (Kindle, Instapaper, Pocket, web, Apple Books) or by category (books, articles, tweets, podcasts) to quickly find the content you need.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.