MCP server
Readwise MCP server
Readwise's official hosted MCP server lets AI search and manage your reading highlights and Reader documents.
- Official server
- Knowledge and memory
Why it matters
What it does and why it matters
Readwise collects highlights from books, articles and documents, and its Reader app stores saved reading. The official hosted MCP server lets an assistant search and list highlights, create and update them, search and list Reader documents, read document details, move documents and add tags.
For leaders, researchers and consultants, years of highlights become a searchable source: "what have I saved about pricing strategy" returns your own reading, not the open web.
The older local server is deprecated, and Readwise now supports the hosted server. It can also delete items, so review changes. Your reading history is personal, so connect only your own account.
It works well alongside a note-taking server such as Obsidian or Notion, so ideas from reading can be turned into notes or plans in the same conversation.
Use cases
Best business use cases
Search highlights
Topic briefs
Organize reading
Add highlights
Talk prep
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read and write: search and read highlights and Reader documents, plus create, edit, tag, move and delete.
-
readwise_search_highlightsSearch your highlights with vector and full-text search.
-
readwise_list_highlightsList highlights, newest first, with filters.
-
readwise_create_highlightsCreate new highlights.
-
readwise_update_highlightEdit highlight text, note, location or tags.
-
reader_search_documentsSearch the full text of your Reader library.
-
reader_list_documentsList Reader documents by location, category or tag.
-
reader_get_document_detailsGet document metadata and full Markdown content.
-
reader_move_documentsMove documents between inbox, later and archive.
-
reader_add_tags_to_documentAdd tags to a Reader document.
Workflows
Example workflows
Prepare a talk
-
1
Name the topic.
-
2
The assistant searches your highlights.
-
3
It groups quotes by theme.
-
4
It drafts an outline with sources.
-
5
You refine the talk.
Tidy the reading list
-
1
Ask for unread Reader documents.
-
2
The assistant lists them.
-
3
It suggests tags.
-
4
It moves old items to archive after approval.
-
5
Your list stays manageable.
Prompts
Example prompts
“What have I highlighted about pricing strategy? Group by theme.”
“List Reader documents saved this month that I have not read.”
“Tag these three articles with "hiring".”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Code: terminal
claude mcp add --transport http readwise https://mcp2.readwise.io/mcp- Hosted server: https://mcp2.readwise.io/mcp (hosted, HTTP).
- Needs: Sign in to your Readwise account when the client prompts (OAuth)..
- Claude Desktop: Docs say: Customize > Connectors > Add custom connector, name Readwise, URL https://mcp2.readwise.io/mcp, then authorize.
Security
Security considerations
-
Personal account
Connect only your own account.
-
Review changes
Review moves and deletes.
-
Hosted server
The older local server is deprecated.
-
Untrusted text
Saved articles are external content.
Related servers
Servers that pair well with it
Obsidian
A community MCP server that lets AI list, read, search, edit, append to and delete notes in an Obsidian vault through the Local REST API plugin.
Notion
Notion's official hosted MCP server lets AI search and read pages, create and update pages and databases, query data and add comments.
Memory
The MCP project's Memory reference server gives AI a local knowledge graph to store people, things and facts and recall them later.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- RAG knowledge assistants Assistants that answer questions from your own documents and show where each answer came from.
- AI Product Development AI agents, knowledge assistants, copilots and document automation built into the way your team already works.
Solutions
View all solutions- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- AI support agent An assistant that answers routine questions from your own content, checks orders and hands anything else to a person.
- Compliance tracking Track filing deadlines, licenses and obligations in one place, with reminders and AI summaries of relevant rule changes.
- Meeting notes automation Transcribe meetings and calls, summarize decisions and push action items into your CRM or project tool.
Industries
View all industries- Healthcare Patient booking, intake forms, internal knowledge assistants and admin automation for clinics and care providers.
- Legal Contract review assistants, knowledge search, intake and document automation for law firms and in-house legal teams.
- Professional services Client portals, proposal drafting, knowledge assistants and internal tools for consultancies, agencies and firms.
- Education and elearning Course platforms, student portals, content workflows and AI tutoring assistants for schools and training companies.
Guides and articles
View all guides and articlesAI models
View all ai models- Cohere Rerank 4 Cohere's multilingual rerank models, which sort search results by relevance, in a best-quality Pro version and a low-latency Fast version.
- Gemini Embedding 2 Google's current embedding model, multimodal: it embeds text, images, video, audio and PDFs for search and retrieval.
- text-embedding-3-large OpenAI's most capable embedding model for search and retrieval, with 3,072-dimension vectors and support for English and other languages.
- text-embedding-3-small OpenAI's efficient, lowest-cost embedding model, with 1,536-dimension vectors for search, retrieval and similarity at scale.
- Cohere Embed v4 Cohere's multimodal embedding model for enterprise search, embedding text, images and mixed documents, with flexible vector sizes and long inputs.
- Voyage 4 Voyage AI's current embedding series, now part of MongoDB, with large, standard and lite models that share one embedding space.
Glossary terms
View all glossary terms- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- Natural language processing Natural language processing is the field of AI that deals with understanding and generating human language, in text or speech.
- Semantic search Semantic search finds results by meaning rather than exact words, so a search for "reset my login" can find an article titled "Forgot your password".
- Chatbot A chatbot is software that holds a conversation with people through text or voice, answering questions or completing simple tasks.
- Embeddings Embeddings are lists of numbers that represent the meaning of text or images, so software can find items that are similar in meaning.
- Vector database A vector database stores embeddings, lists of numbers that represent meaning, and quickly finds the ones most similar to a query.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. Readwise hosts it. The older local server is deprecated.
Yes. It covers highlights and Reader documents.
Yes. It can create, edit, tag, move and delete items.