Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for Readwise Reader API
This server exposes Readwise Reader actions through MCP so an agent can manage your reading library. It supports saving documents, listing and filtering items, updating metadata, deleting documents, listing tags, and topic search, with converted text content for easier agent use.
Builders who want their agent to read, search, and manage a Readwise Reader library.
You can keep research and reading materials inside Readwise Reader while your agent saves, finds, and updates them for you.
What it does
Secure token authentication
Uses the `READWISE_TOKEN` environment variable for API access.
Document management
Supports saving, listing, updating, and deleting documents with full metadata.
Tag listing and filtering
Lets you list tags and filter documents by tag, location, category, and update time.
Pagination support
Handles large document sets with page cursors.
LLM-friendly content conversion
Converts HTML to clean text through r.jina.ai before returning content.
Topic search
Searches titles, summaries, notes, and tags with regex matching.
How to get it
- 1Run
npm install npm run build
README
Readwise Reader MCP Server
A Model Context Protocol (MCP) server for the Readwise Reader API, built with TypeScript and the official Claude SDK.
Features
- Secure Authentication: Uses environment variables for token storage
- Document Management: Save, list, update, and delete documents with complete metadata
- Tag Management: List and filter by tags
- Rich Filtering: Filter documents by location, category, tags, and more
- Pagination Support: Handle large document collections
- LLM-Friendly Content: HTML content automatically converted to clean text using r.jina.ai
- Complete Data Access: Returns full document information including content, metadata, and timestamps
API Documentation
For detailed information about the Readwise Reader API endpoints, parameters, and examples, please refer to the official API documentation:
📖 Readwise Reader API Documentation
This MCP server implements all the core endpoints described in the official documentation.
Installation
npm install
npm run build
Configuration
With Claude Desktop
-
Build the MCP server:
npm install npm run build -
Get your Readwise access token from: https://readwise.io/access_token
-
Add the server to your Claude Desktop configuration. Open your Claude Desktop settings and add this to your MCP servers configuration:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:%APPDATA%\Claude\claude_desktop_config.json{ "mcpServers": { "readwise-reader": { "command": "node", "args": ["/path/to/your/reader_readwise_mcp/dist/index.js"], "env": { "READWISE_TOKEN": "your_readwise_access_token_here" } } } }Replace:
/path/to/your/reader_readwise_mcpwith the actual path to this project directoryyour_readwise_access_token_herewith your actual Readwise access token
-
Restart Claude Desktop
Available Tools
readwise_save_document
Save a document (URL or HTML content) to Readwise Reader.
Parameters:
url(required): URL of the document to savehtml(optional): HTML content of the documenttags(optional): Array of tags to addlocation(optional): Location to save (new,later,shortlist,archive,feed)category(optional): Document category (article,book,tweet,pdf,email,youtube,podcast)
readwise_list_documents
List documents from Readwise Reader with optional filtering. Returns complete document information including metadata and LLM-friendly text content.
Parameters:
id(optional): Filter by specific document IDupdatedAfter(optional): Filter documents updated after this date (ISO 8601)location(optional): Filter by document locationcategory(optional): Filter by document categorytag(optional): Filter by tag namepageCursor(optional): Page cursor for paginationwithHtmlContent(optional): ⚠️ PERFORMANCE WARNING: Include HTML content in the response. This significantly slows down the API. Only use when explicitly requested by the user or when raw HTML is specifically needed for the task.withFullContent(optional): ⚠️ PERFORMANCE WARNING: Include full converted text content in the response. This significantly slows down the API as it fetches and processes each document's content. Only use when explicitly requested by the user or when document content is specifically needed for analysis/reading. Default: false for performance.
Returns: Complete document objects with all available fields:
id,title,author,url,source_url,summarypublished_date,image_url,location,categorytags,created_at,updated_atcontent: LLM-friendly text content (converted from source_url or url via r.jina.ai)
readwise_update_document
Update a document in Readwise Reader.
Parameters:
id(required): Document ID to updatetitle(optional): New titleauthor(optional): New authorsummary(optional): New summarypublished_date(optional): New published date (ISO 8601)image_url(optional): New image URLlocation(optional): New locationcategory(optional): New category
readwise_delete_document
Delete a document from Readwise Reader.
Parameters:
id(required): Document ID to delete
readwise_list_tags
List all tags from Readwise Reader.
Parameters: None
readwise_topic_search
Search documents in Readwise Reader by topic using regex matching on title, summary, notes, and tags.
Parameters:
searchTerms(required): Array of search terms to match against document content (case-insensitive regex matching)
Returns: Search results with matching documents including:
- Search terms used
- Total number of matches
- Complete document objects with all available metadata (same fields as
readwise_list_documents)
Authentication
The server requires a Readwise access token to be provided via the READWISE_TOKEN environment variable. This token is used to authenticate all API requests to Readwise Reader.
Security Note: The token is stored in your MCP configuration and never exposed through Claude or the tools interface.
Rate Limits
- Default: 20 requests/minute
- Document CREATE/UPDATE: 50 requests/minute
- 429 responses include "Retry-After" header
License
MIT
Files in the repo
- src
- .gitignore
- env.example
- LICENSE
- package-lock.json
- package.json
- README.md
- tsconfig.json
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros