Content
# WeChat Reading MCP Server
A tool that provides MCP (Model Context Protocol) services for WeChat Reading, supporting the provision of WeChat Reading books, notes, and highlight data to large language model clients that support MCP, such as Claude Desktop.
## Features
- Get bookshelf information from WeChat Reading
- Search for books in the bookshelf
- Get notes and highlights of books
- Get popular book reviews of books
- Support organizing notes and highlights by chapter
- Seamless integration with LLM clients that support the MCP protocol
## Main Tools
1. **get_bookshelf** - Get all books on the user's bookshelf
- Returns basic book information, including title, author, translator, and category, etc.
2. **search_books** - Search for books on the user's bookshelf by keyword
- Supports fuzzy matching and exact matching
- Optional to include detailed information
- Maximum number of results can be set
3. **get_book_notes_and_highlights** - Get all highlights and notes for a specified book
- Supports organizing results by chapter
- Supports filtering highlight styles
- Returns structured data for LLM understanding
4. **get_book_best_reviews** - Get popular book reviews for a specified book
- Supports setting the number of returns
- Supports paged browsing
- Includes ratings, likes, and reviewer information
## Installation and Usage
### Prerequisites
- Node.js 16.x or higher
- WeChat Reading account and valid Cookie
### Installation Guide
See: [Weread MCP Server Usage Guide](https://chenge.ink/article/post20250505)
### Integration with Claude Desktop
There are several ways to integrate with Claude Desktop:
#### Method 1: Use via npx (simplest, recommended)
1. Open Claude Desktop
2. Go to Settings -> MCP Configuration
3. Add a tool using the following JSON configuration:
```json
{
"mcpServers": {
"mcp-server-weread": {
"command": "npx",
"args": ["-y", "mcp-server-weread"],
"env": {
// Method 1: Use Cookie Cloud (recommended)
"CC_URL": "https://cc.chenge.ink", // Cookie Cloud URL
"CC_ID": "Your ID", // Cookie Cloud ID
"CC_PASSWORD": "Your Password" // Cookie Cloud Password
// Or Method 2: Provide Cookie directly
// "WEREAD_COOKIE": "Your WeChat Reading Cookie"
}
}
}
}
```
#### Method 2: Use after global installation
1. Install the package globally:
```bash
npm install -g mcp-server-weread
```
2. Use in Claude configuration:
```json
{
"mcpServers": {
"mcp-server-weread": {
"command": "mcp-server-weread",
"env": {
// Configure environment variables in the same way as above
}
}
}
}
```
> Tip: Providing environment variables directly in the Claude configuration is more convenient and eliminates the need to set up a .env file. It is recommended to use this method.
## CookieCloud Configuration Instructions
In order to solve the problem of frequent Cookie expiration, which requires re-acquiring and updating environment variables. This project supports [CookieCloud](https://github.com/easychen/CookieCloud) service to automatically synchronize and update Cookies. CookieCloud is an open-source cross-browser Cookie synchronization tool that supports self-built servers.
### Configuration steps:
Install the browser extension
Edge Store: [CookieCloud for Edge](https://microsoftedge.microsoft.com/addons/detail/cookiecloud/bffenpfpjikaeocaihdonmgnjjdpjkeo)
Chrome Store: [CookieCloud for Chrome](https://chromewebstore.google.com/detail/cookiecloud/ffjiejobkoibkjlhjnlgmcnnigeelbdl)
### Configure the CookieCloud plugin
Server address: Use the default server https://cc.chenge.ink or enter the address of your self-built server
Click "Automatically generate password"
Enter "weread" in the synchronized domain keywords
Click "Save" and then click "Manual Sync" to ensure the configuration takes effect
[Optional] If you need the plugin to automatically keep alive, you can enter https://weread.qq.com in the keep-alive field, and the plugin will automatically refresh the Cookie
Configure CookieCloud variables in MCP Json:
CC_URL=Your CookieCloud server address (or use my default server address https://cc.chenge.ink)
CC_ID=Your CookieCloud user UUID
CC_PASSWORD=Your CookieCloud password
Note: After configuring CookieCloud, the system will prioritize using CookieCloud to obtain the Cookie. If it fails, it will use the value of the WEREAD_COOKIE environment variable.
## Cookie Acquisition Method
The WeChat Reading Cookie can be obtained through the following steps:
1. Log in to the [WeChat Reading web version](https://weread.qq.com/) using the Chrome browser
2. Press F12 to open the developer tools and switch to the Network tab
3. Refresh the page and find the request for weread.qq.com in the request list
4. Find the Cookie field in the Headers and copy its complete content
5. Add the copied content to the WEREAD_COOKIE variable in the MCP Json or .env file
## Usage Examples
Here are some examples of conversations with LLM:
**Get bookshelf information**
```
User: Help me view my WeChat Reading bookshelf
LLM: I will retrieve your WeChat Reading bookshelf information.
[LLM calls get_bookshelf tool]
I have retrieved 208 books from your WeChat Reading bookshelf. Here are some of the books:
1. "The Hidden Self" - David Eagleman
2. "Thinking, Fast and Slow" - Daniel Kahneman
3. "Sapiens: A Brief History of Humankind" - Yuval Noah Harari
...
```
**Search for specific books**
```
User: Help me find books about psychology
LLM: I will search your bookshelf for books related to psychology.
[LLM calls search_books tool with keyword="psychology"]
I found 3 books related to psychology on your bookshelf:
1. "Thinking, Fast and Slow" - Daniel Kahneman (Progress: 75%)
2. "Crowds: A Study of the Popular Mind" - Gustave Le Bon (Progress: 50%)
3. "Psychology and Life" - Richard Griggs (Progress: 30%)
Would you like to know more about any of these books?
```
**Get notes and highlights**
```
User: Help me organize the notes for the book "Thinking, Fast and Slow"
LLM: I will retrieve the notes and highlights for "Thinking, Fast and Slow".
[LLM calls search_books tool to find the book ID]
[LLM calls get_book_notes_and_highlights tool]
Here are your notes and highlights in "Thinking, Fast and Slow" (organized by chapter):
Chapter 1: The Systems
- Highlight: "System 1 operates automatically and quickly, with little or no effort and no sense of voluntary control."
- Your note: "System 1 is responsible for intuition and quick judgments, System 2 is responsible for slow, rational thinking."
Chapter 3: The Anchoring Effect
- Highlight: "The anchoring effect refers to the tendency to rely too heavily on one piece of information when making decisions."
...
```
**Get popular book reviews**
```
User: What are some popular book reviews for "Principles"?
LLM: I will find popular book reviews for "Principles".
[LLM calls search_books tool to find the book ID]
[LLM calls get_book_best_reviews tool]
Here are the popular book reviews for "Principles":
1. Reviewer "Thinker" (Rating: 5 stars):
"This is a book about how to think. Dalio summarizes his years of experience into actionable principles to help us make better decisions. I especially like his view of 'Pain + Reflection = Progress', which is very practical."
👍 182 | 💬 23
2. Reviewer "Investment Learner" (Rating: 4 stars):
"The essence of the Bridgewater Fund founder's thoughts is worth reading repeatedly. The working principles section of the book is especially helpful for managers. It is recommended to read the life principles first, and then the working principles."
👍 94 | 💬 12
...
```
## License
MIT
## Contribution
Welcome to submit Pull Requests or Issues to improve this project.
