WeReadSAFE
微信读书MCP
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
一个为微信读书提供 MCP 服务的工具
微信读书 MCP Server 是一个为微信读书提供 MCP(Model Context Protocol)服务的工具,支持将微信读书的书籍、笔记和划线数据提供给支持MCP的大语言模型客户端,如Cursor、Claude Desktop。
功能特点
- 从微信读书获取书架信息
- 搜索书架中的图书
- 获取图书的笔记和划线
- 获取图书的热门书评
- 支持按章节组织笔记和划线
- 与支持MCP协议的LLM客户端无缝集成
主要工具
- get_bookshelf - 获取用户书架上所有书籍
- 返回书籍基本信息,包括书名、作者、译者和分类等
- search_books - 通过关键词检索用户书架上的书籍
- 支持模糊匹配和精确匹配
- 可选是否包含详细信息
- 可设置最大结果数量
- get_book_notes_and_highlights - 获取指定书籍的所有划线和笔记
- 支持按章节组织结果
- 支持筛选划线样式
- 返回结构化的数据以便于LLM理解
- get_book_best_reviews - 获取指定书籍的热门书评
- 支持设置返回数量
- 支持分页浏览
- 包含评分、点赞数和评论者信息
安装与使用
先决条件
- Node.js 16.x 或更高版本
- 微信读书账号和有效的Cookie
安装教程
详见:
与Claude Desktop集成
有多种方式可以与Claude Desktop集成:
方式一:通过 npx 使用(最简单,推荐)
- 打开Claude Desktop
- 进入设置 -> MCP配置
- 添加工具,使用以下JSON配置:
{
"mcpServers": {
"mcp-server-weread": {
1a6fca66749eOBSERVED · 2026-09-29Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server-weread --env CC_PASSWORD=${CC_PASSWORD} -- npx -y [email protected]{
"mcpServers": {
"mcp-server-weread": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"CC_PASSWORD": "${CC_PASSWORD}"
}
}
}
}Exposed tools (4)
4 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_book_best_reviews | read | Get popular reviews for a specific book |
get_book_notes_and_highlights | read | Get all highlights and notes for a specific book, organized by chapter |
get_bookshelf | read | Get all books in the user |
search_books | read | Search for books in the user |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
.DS_Store
.DS_Store
axios, dotenv, @types/node, typescript
.cache/weread-cache.json
.cache/weread-data.db
Gates applied: no_behavioural_pass.
1a6fca66749efull audit observations/trust-audit/mcp-server/freestylefly__weread.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-29 | 1a6fca66749e | SAFE | B | 89 | first audit |
Questions
What is the WeRead MCP server?
微信读书MCP
What tools does WeRead expose?
4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is WeRead safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does WeRead need?
It reads CC_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does WeRead run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-server-weread at 0.2.2.
How current is this page?
The grade is for one exact copy of the source (1a6fca66749e), read on 2026-09-29. The repository is watched and re-audited when it changes.