readwise-reader-mcp

readwise-reader-mcp

Enables integration with Readwise Reader API to save, retrieve, update, and manage documents, tags, and filtering in your Readwise Reader account.

Category
访问服务器

README

Readwise Reader MCP Server

A Model Context Protocol (MCP) server for integrating with Readwise Reader API. This server provides tools for saving, retrieving, updating, and managing documents in your Readwise Reader account.

Features

  • 🔐 Authentication: Secure token-based authentication with Readwise Reader
  • 📚 Document Management: Save, list, update, and delete documents
  • 🏷️ Tag Management: List and organize your tags
  • 🔍 Advanced Filtering: Filter documents by location, category, tags, and dates
  • 🌐 HTTP Transport: Streamable HTTP server for easy integration
  • 🐳 Docker Support: Containerized deployment ready

Available Tools

  1. readwise_authenticate - Authenticate with Readwise Reader API
  2. readwise_save_document - Save a new document (URL or HTML content)
  3. readwise_list_documents - List documents with filters
  4. readwise_update_document - Update document metadata
  5. readwise_delete_document - Delete a document
  6. readwise_list_tags - List all available tags
  7. readwise_get_document_content - Get full content of a specific document

Quick Start

Prerequisites

  1. Python 3.9+ installed
  2. Readwise Account with Reader access
  3. Access Token from https://readwise.io/access_token

Installation

# Clone the repository
git clone <repository-url>
cd readwise-reader-mcp

# Install the package
pip install -e .

Configuration

  1. Copy the example environment file:
cp .env.example .env
  1. Edit .env and add your Readwise access token:
READWISE_ACCESS_TOKEN=your_token_here

Running the Server

Local Development

# Run with default settings (port 8000)
readwise-reader-mcp

# Run on custom port
readwise-reader-mcp --port 9000

# Show help
readwise-reader-mcp --help

Using Docker

Build and run with Docker:

# Build the image
docker build -t readwise-reader-mcp .

# Run with environment file
docker run -p 8000:8000 --env-file .env readwise-reader-mcp

# Or run with inline environment variable
docker run -p 8000:8000 -e READWISE_ACCESS_TOKEN=your_token readwise-reader-mcp

Docker Compose

version: '3.8'
services:
  readwise-reader-mcp:
    build: .
    ports:
      - "8000:8000"
    environment:
      - READWISE_ACCESS_TOKEN=your_token_here
      - LOG_LEVEL=INFO

Integration with Claude Desktop

Add this configuration to your Claude Desktop settings:

{
  "mcpServers": {
    "readwise-reader": {
      "command": "readwise-reader-mcp",
      "args": ["--port", "8000"],
      "env": {
        "READWISE_ACCESS_TOKEN": "your_token_here"
      }
    }
  }
}

Or use WebSocket connection:

{
  "mcpServers": {
    "readwise-reader": {
      "command": "ws://localhost:8000/ws"
    }
  }
}

API Usage Examples

Save a Document

# Save a web page by URL
readwise_save_document({
    "url": "https://example.com/article",
    "title": "Interesting Article",
    "tags": ["tech", "ai"],
    "location": "later"
})

# Save HTML content directly
readwise_save_document({
    "html": "<html><body><h1>My Article</h1>...</body></html>",
    "title": "Custom Content",
    "category": "article"
})

List Documents

# List recent documents
readwise_list_documents()

# Filter by location
readwise_list_documents({
    "location": "archive",
    "category": "article"
})

# Get documents updated after a date
readwise_list_documents({
    "updated_after": "2024-01-01T00:00:00Z"
})

Update Document

readwise_update_document({
    "document_id": "doc_id_here",
    "title": "New Title",
    "location": "archive"
})

Document Locations

  • new - New/Inbox (default for saved documents)
  • later - Read Later list
  • shortlist - Shortlist
  • archive - Archived documents

Document Categories

  • article - Web articles
  • email - Email content
  • rss - RSS feed items
  • highlight - Highlights
  • note - Personal notes
  • pdf - PDF documents
  • epub - EPUB books
  • tweet - Twitter content
  • video - Video content

Rate Limits

The Readwise Reader API has the following rate limits:

  • General requests: 20 requests per minute
  • Document saves/updates: 50 requests per minute

The client automatically handles rate limit errors and includes appropriate retry information.

Error Handling

The server provides detailed error responses:

{
  "success": false,
  "error": "Authentication failed: Invalid token"
}

Common errors:

  • Authentication errors: Invalid or expired token
  • Rate limiting: Too many requests
  • Validation errors: Missing required parameters
  • API errors: Readwise service issues

Development

Setup Development Environment

# Install with development dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Format code
black src/

# Lint code
ruff check src/

Project Structure

readwise-reader-mcp/
├── src/
│   └── readwise_reader_mcp/
│       ├── __init__.py
│       ├── client.py          # Readwise API client
│       ├── models.py          # Pydantic models
│       └── server.py          # FastMCP server
├── tests/                     # Test files
├── Dockerfile                 # Container configuration
├── pyproject.toml            # Project configuration
├── .env.example              # Environment template
└── README.md

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests for new functionality
  5. Run the test suite
  6. Submit a pull request

License

MIT License - see LICENSE file for details.

Support

Changelog

0.1.0

  • Initial release
  • Basic document management tools
  • HTTP transport support
  • Docker containerization
  • Authentication and error handling

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选