Readwise MCP. Query Your Entire Reading History in Minutes.
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 agent directly to your personal knowledge base. It lets you search, read, and retrieve every highlight, book snippet, and saved article from your unified Readwise library.
Your agent can instantly pull quotes from Kindle, Apple Books, and web sources so you don't have to manually dig through PDFs or old notes.
What your AI agents can do
Check auth status
Verifies if your Readwise access token is currently valid and working for the AI agent.
Get reader document
Retrieves the full text content of a specific article or document ID saved in Readwise Reader.
List books
Returns a list and metadata for all books and sources stored in your Readwise account.
Query every snippet or quote you've saved across all your sources (Kindle, web, etc.) using list_highlights.
List all books and original sources currently cataloged in your Readwise account via list_books.
Get the full text of a specific article or document saved within Readwise Reader using get_reader_document.
List and analyze all custom tags you use to categorize your research notes using list_tags.
See a list of all articles, sources, and books available in the Readwise database with list_reader_documents.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Readwise MCP Server: 6 Tools for Knowledge Retrieval
These six tools allow your agent to query the full scope of your Readwise account—from individual highlights to entire books and articles.
019d75fdcheck auth status
Verifies if your Readwise access token is currently valid and working for the AI agent.
019d75fdget reader document
Retrieves the full text content of a specific article or document ID saved in Readwise Reader.
019d75fdlist books
Returns a list and metadata for all books and sources stored in your Readwise account.
019d75fdlist highlights
Retrieves a filtered or bulk list of all individual quotes, snippets, and highlights from your entire reading history.
019d75fdlist reader documents
Provides an index listing the titles and metadata for all documents stored in Readwise Reader.
019d75fdlist tags
Outputs a list of every unique tag you have applied to your highlights or notes within Readwise.
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 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
Check your Readwise connection status first using check_auth_status; it confirms whether your agent's access token is valid and ready to go.
Your AI client talks straight to your entire personal knowledge base, letting you search, read, and pull every single highlight, snippet, and saved article from your unified Readwise library. It’s like having a perfect memory for everything you’ve ever learned.
When you need to dig deep into what you've saved, the list_highlights tool pulls up a massive list of individual quotes, snippets, and highlights across every source—Kindle, web browsers, books—so your agent can query them all at once. You don’t have to manually scroll through PDFs or old notes; it just spits out exactly what you asked for.
To organize that mountain of info, the list_tags tool outputs a comprehensive list of every unique tag you've slapped on your research notes. Your agent can use these tags to filter and categorize massive amounts of data instantly.
For structured browsing, you can run list_books, which returns a full list and all the metadata for every book or source currently stored in your Readwise account. It tells you exactly what material is available before you even start querying it.
Need the full text of an article? Use list_reader_documents to get an index listing of all articles, sources, and books saved within Readwise Reader; then, run get_reader_document with a specific document ID to pull the complete raw text content. This is crucial for deep analysis where you need more than just a snippet.
Your agent can also cross-reference data by running list_tags alongside list_highlights, letting you see which ideas are associated with your key organizational tags across all sources. The whole system works together to make synthesis possible, so you can ask complex questions like, "What did I read about quantum computing last year that was tagged 'Physics'?" and get a clean answer immediately.
It’s built for retrieval: Your agent retrieves the full text of an article using get_reader_document even if all you initially saw was a small snippet. You can verify everything works by running check_auth_status, making sure your connection stays live and solid.
Basically, it turns reading into searchable data. If you're working with dense academic material or just trying to keep track of ideas from twenty different sources, this is what you need.
How Readwise MCP Works
- 1 First, authorize the Readwise MCP server in your workspace. You'll need to generate a dedicated Access Token from readwise.io.
- 2 Second, chat with your AI client and direct it to perform an action (e.g., 'Find all highlights about productivity'). The agent uses the available tools like
list_highlightsto query Readwise. - 3 Third, the server returns the raw data—the quotes, documents, or tag lists—which the agent then synthesizes into a readable answer for you.
The bottom line is: You tell your AI client what knowledge you need; the MCP Server finds it in Readwise and hands it back.
Who Is Readwise MCP For?
This is for anyone who reads more than they write. It helps researchers, writers, and students stop losing brilliant ideas in an avalanche of saved articles. If you're tired of manually searching through old PDFs or scattered notes to prove a point, this server connects your reading history directly into your AI workflow.
Uses the agent to query list_highlights for specific quotes across multiple books and sources, building literature reviews without leaving their writing environment.
Asks the AI to pull definitions or conceptual statements from saved articles (via get_reader_document) to ensure consistency in new documentation drafts.
Uses list_books and list_tags to quickly survey all sources related to a thesis topic, building study guides from centralized highlights.
What Changes When You Connect
- Stop hunting through folders. Use
list_highlightsto search every quote you’ve ever saved, letting your agent pull specific ideas from books or articles instantly. - Build robust research arguments by cross-referencing data. The combination of
list_books,list_tags, andlist_highlightslets the AI connect disparate sources automatically. - Full article context is available when you need it. Use
get_reader_documentto fetch the complete Markdown for a saved Readwise Reader article, not just a summary. - Know what you're working with. The
list_tagstool lets your agent map out how you categorize knowledge, giving immediate structure to complex data sets. - Verify connection status immediately by running
check_auth_status. This ensures the AI doesn't fail halfway through a critical research task.
Real-World Use Cases
Synthesizing for a Proposal
A marketing manager needs to write a competitive analysis. Instead of opening 15 PDFs, they ask their agent: 'Find me every time I mentioned Competitor X's weakness in my notes.' The agent uses list_highlights and list_tags to instantly pull all relevant quotes across years of saved reading.
Deep Dive on a Topic
A student is writing an essay on AI ethics. They ask their agent: 'Show me everything I read about bias.' The agent uses list_tags to find the relevant tag, and then runs list_highlights to retrieve all associated quotes from across various sources.
Contextualizing a Concept
A writer is stalled on a scene. They ask their agent: 'What were my thoughts on existential dread when I read that article last month?' The agent uses list_reader_documents to find the right source and then get_reader_document to pull the specific text.
Auditing Knowledge Gaps
A knowledge worker reviews their personal library. They ask: 'What topics have I saved notes on, but haven't tagged yet?' The agent uses list_books and list_tags to give a clear map of the content versus its organization.
The Tradeoffs
Trying to search live data
Asking the agent, 'What is happening in the news right now?' The server cannot pull real-time external data; it only accesses your stored Readwise archive.
→
Only query what you've saved. If you want current events, use a general search tool. To find past insights, run list_highlights or specify an article ID with get_reader_document.
Assuming full document text access
Asking the agent to summarize a 50-page PDF that was never uploaded. The server only has access to what you explicitly saved.
→
Use list_reader_documents first to check if the file exists in your Reader library, then use get_reader_document with the ID.
Ignoring authentication
Attempting complex queries without confirming token validity. The agent will fail on a cryptic 401 error.
→
Always run check_auth_status first to confirm your credentials are active before initiating any large data retrieval tasks.
When It Fits, When It Doesn't
Use this server if your core task is synthesizing, organizing, or retrieving ideas from content you have already read and saved. It's the perfect 'Second Brain' connection. Don't use it if your goal is real-time data—like checking stock prices, live meeting schedules, or fetching fresh news headlines; those require different API connectors.
If you need to find out what quotes you remember from a specific book title, run list_books and then target the relevant ID. If you just want to know how you organize your notes, check list_tags. This server deals with structured knowledge retrieval; it’s not a general web search engine.
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 6 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually sifting through saved highlights takes forever.
Think about the last time you wrote an essay and realized you had three brilliant quotes from books, two snippets from articles, and one key definition from a PDF—all scattered across your hard drive or various note apps. You spend hours searching: 'Where did I write that down?' Copying, pasting, renaming, deleting... it’s painful.
With the Readwise MCP Server, you just tell your agent what idea you need. It runs `list_highlights` and pulls every relevant quote directly from your centralized archive. You get the synthesis immediately; no digging required.
Readwise MCP Server: Direct access to all stored reading data.
You used to have to export, clean, and re-index your highlights just to make them readable by another tool. You had to manually track which quotes came from Kindle versus a web article.
Now, the agent handles the source tracking automatically. It can use `list_reader_documents` to get the full context of an article *and* cross-reference that with your tags using `list_tags`. The data is clean and actionable.
Common Questions About Readwise MCP
How do I start using Readwise MCP Server? (check_auth_status) +
You must first run check_auth_status to validate your token. This confirms the connection is live and working before you attempt any data retrieval.
Can I search for highlights across multiple types of content? (list_highlights) +
Yes, list_highlights queries all sources—Kindle, web, Apple Books—using a single endpoint. It doesn't care if the snippet came from an e-book or an article.
How do I get the full text of an article? (get_reader_document) +
You must use get_reader_document and provide a specific document ID. This returns the raw, complete Markdown content for that piece.
What if I want to know what tags are available? (list_tags) +
Run list_tags. This shows you every custom tag used in your Readwise account. You can then ask the agent to filter highlights by a specific tag.
Is there a way to list all my books? (list_books) +
Yes, list_books gives you an index of every book and original source in your Readwise database. It's great for seeing the scope of your reading material.
What does running `list_reader_documents` show me about my saved articles in Readwise Reader? +
It returns a list of all documents stored in your Readwise Reader, including metadata like titles and dates. You can browse the entire content library before pulling specific text using get_reader_document.
How do I use `list_books` to understand the scope of sources available for highlighting? +
Running list_books displays every book and source type connected to your Readwise account. This helps you see exactly what kind of original material—like PDFs or Kindle titles—your highlights are drawn from.
If my AI client fails to connect, how should I troubleshoot the server using `check_auth_status`? +
You must run check_auth_status first. This verifies that your Readwise access token is still valid and active before you attempt any complex data retrievals or searches.
Where do I obtain my Readwise Access Token? +
You can quickly find or generate your specific access token by logging into your Readwise account and directly visiting https://readwise.io/access_token. Copy the alphanumeric token presented there and insert it directly into the prompt required by this integration.
Can the AI add native highlights or upload PDFs to Reader for me? +
Currently, the integration server functions on a Read-Only standard format designed specifically to fetch existing knowledge. It fetches metadata or full-text values from highlights, tags, and Reader items, but it doesn't support publishing or updating new sources back to Readwise natively.
Does it also search through to my saved Readwise Reader feed? +
Yes. Tools like list_reader_documents and get_reader_document are designated explicitly for extracting articles or stored reads directly residing inside your connected Readwise Reader account, keeping both typical highlights and Reader data separate but reachable.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Elastic Enterprise Search
Manage enterprise search via Elastic — search engines and documents, handle indexing, and monitor search analytics directly from any AI agent.
OpenLaws
Access validated legal data via OpenLaws — search statutes, regulations, case law, validate citations, and track legislative changes directly from any AI agent.
Domo
Manage Domo users and groups directly from your AI agent — create, update, and delete users, or organize them into groups for better governance.
You might also like
Hiver
Turn Gmail into a helpdesk with shared labels, email assignment, and SLA tracking that works inside the inbox your team already uses.
Fountain
Automate high-volume hiring, manage applicant funnels, and track hiring goals via AI agents with Fountain.
ClickUp
Manage tasks and projects via ClickUp — track work, monitor spaces, and manage team productivity directly from any AI agent.