WeRead
A lightweight bridge server that connects WeChat Reading (WeRead) data with Claude Desktop, allowing seamless access to reading notes and book collections through natural language interactions.
What is WeRead?
WeRead is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to lightweight bridge server that connects wechat reading (weread) data with claude desktop, allowing seamless access to reading notes and book collections through natural language interactions.
A lightweight bridge server that connects WeChat Reading (WeRead) data with Claude Desktop, allowing seamless access to reading notes and book collections through natural language interactions.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A lightweight bridge server that connects WeChat Reading (We
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx weread-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use WeRead
WeRead MCP Server is a lightweight bridge that connects WeChat Reading (WeRead) to Claude Desktop and other MCP clients, giving AI assistants natural-language access to your reading library. It exposes your bookshelf, reading highlights, chapter annotations, and popular book reviews through four focused tools. Readers and knowledge workers who use WeRead to annotate books can use this server to query, organize, and analyze their reading notes through conversation.
Prerequisites
- Node.js 16.x or later installed
- A WeChat Reading account with books and notes
- A CookieCloud server (self-hosted or the public default) OR a direct WeRead browser cookie
- An MCP client such as Claude Desktop
Obtain your WeRead authentication cookie
Log in to WeRead in your browser, open DevTools, and copy the full cookie header from a weread.qq.com request. You will use this as the WEREAD_COOKIE value, or sync it via CookieCloud.
Install the package globally
Install mcp-server-weread from npm so the command is available system-wide.
npm install -g mcp-server-wereadConfigure Claude Desktop with your credentials
Add the server block to Claude Desktop's config file. Use WEREAD_COOKIE for direct auth, or set CC_URL, CC_ID, and CC_PASSWORD if you use CookieCloud for automatic cookie management.
{
"mcpServers": {
"weread": {
"command": "npx",
"args": ["-y", "mcp-server-weread"],
"env": {
"WEREAD_COOKIE": "<your-weread-cookie>"
}
}
}
}Or configure with CookieCloud
If you use CookieCloud for automatic cookie sync, set these three environment variables instead of WEREAD_COOKIE. The server will prefer CookieCloud and fall back to WEREAD_COOKIE if sync fails.
{
"mcpServers": {
"weread": {
"command": "npx",
"args": ["-y", "mcp-server-weread"],
"env": {
"CC_URL": "https://cc.chenge.ink",
"CC_ID": "<your-cookiecloud-uuid>",
"CC_PASSWORD": "<your-cookiecloud-password>"
}
}
}
}Restart Claude Desktop and query your library
After saving the config and restarting Claude Desktop, ask it to list your bookshelf or retrieve notes from a specific book.
WeRead Examples
Client configuration
Claude Desktop config using direct WeRead cookie authentication.
{
"mcpServers": {
"weread": {
"command": "npx",
"args": ["-y", "mcp-server-weread"],
"env": {
"WEREAD_COOKIE": "<your-weread-cookie>"
}
}
}
}Prompts to try
Example natural-language queries for your WeRead library.
- "Show me all the books on my WeRead bookshelf"
- "Find psychology-related books in my library"
- "Get all my highlights and notes from 'Thinking, Fast and Slow'"
- "What are the most popular reviews for 'Principles' by Ray Dalio?"
- "Organize my notes from the last chapter of Atomic Habits into bullet points"Troubleshooting WeRead
Authentication fails or bookshelf returns empty results
Your WeRead cookie may have expired. Log in to weread.qq.com again, copy a fresh cookie from DevTools (Network tab, any weread.qq.com request, Cookie header), and update WEREAD_COOKIE in your config.
CookieCloud sync fails and falls back to empty cookie
Verify CC_URL is reachable and CC_ID / CC_PASSWORD are correct. Test the CookieCloud endpoint directly: curl "$CC_URL/get/$CC_ID" should return JSON with cookie data. If the server is down, switch to the direct WEREAD_COOKIE approach.
npx command not found or module fails to load
Ensure Node.js 16+ is installed ('node --version'). Try 'npm install -g mcp-server-weread' for a global install, then use 'mcp-server-weread' as the command instead of npx.
Frequently Asked Questions about WeRead
What is WeRead?
WeRead is a Model Context Protocol (MCP) server that lightweight bridge server that connects wechat reading (weread) data with claude desktop, allowing seamless access to reading notes and book collections through natural language interactions. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install WeRead?
Follow the installation instructions on the WeRead GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with WeRead?
WeRead works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is WeRead free to use?
Yes, WeRead is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
WeRead Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to WeRead? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up WeRead in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use WeRead?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.