XiaohongshuSAFE
企业级小红书MCP Node.js重构 - 支持多账号矩阵管理、反风控、数据采集与发布
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
基于现代化Node.js技术栈的小红书MCP(Model Context Protocol)服务器,提供企业级多账号矩阵管理和反风控功能。 暂停维护
🌟 核心特性
🔐 多账号管理
- 无限账号支持:支持无限数量的小红书账号管理
- 独立环境:每个账号使用独立的浏览器指纹和代理环境
- 状态监控:实时监控账号登录状态和健康状况
- Cookie管理:自动维护登录状态,支持Cookie持久化
🛡️ 反风控系统
- 浏览器指纹伪造:完整的UA、硬件、地理位置模拟
- 行为模拟:智能鼠标轨迹、键盘输入、页面滚动
- 特征清理:移除WebDriver、CDP等自动化检测特征
- 代理轮换:支持HTTP/SOCKS5代理池,智能轮换
🚀 任务调度
- 并发执行:支持多任务并发执行,可配置并发数
- 定时任务:基于Cron表达式的定时任务调度
- 重试机制:智能重试和失败恢复
- 任务监控:实时任务状态追踪和历史记录
📊 数据采集
- 内容搜索:关键词搜索、话题搜索、用户搜索
- 笔记详情:获取完整的笔记内容和互动数据
- 用户信息:获取用户基本信息和统计数据
- 评论采集:获取笔记评论和互动信息
- 热门内容:获取各分类热门内容
🎛️ 管理后台
- Web界面:基于Express.js的现代化管理界面
- 实时监控:实时任务状态、系统资源监控
- 数据可视化:图表展示账号数据、任务统计
- 配置管理:可视化配置代理、指纹、任务参数
🏗️ 技术架构
┌─────────────────────────────────────────────────────────────────┐ │ 系统架构总览 │ └─────────────────────────────────────────────────────────────────┘ ┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐ │ AI客户端群 │ │ API网关层 │ │ 小红书平台 │ │ Claude/Cursor │◄──►│ Express+MCP │◄──►│ 多账号并发 │ │ VSCode/CLI工具 │ │ WebSocket │ │ 自动化操作 │ └─────────────────┘ └─────────────────┘ └─────────────────┘ │ ┌───────────────┼───────────────┐ ▼ ▼ ▼ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ Directus │ │ MySQL │ │ 反风控引擎 │ │ 管理后台 │ │ 数据中心 │ │ Stealth+ │ │ (零配置) │ │ (统一前缀) │ │ Fingerprint │ └─────────────┘ └─────────────┘ └─────────────┘ │ │ │ └───────────────┼───────────────┘ ▼ ┌─────────────────────────────────────────────────┐ │ 浏览器实例池 │
3795efa4b15eOBSERVED · 2026-10-07Connect
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 xiaohongshu-mcp-nodejs --env CORS_CREDENTIALS=${CORS_CREDENTIALS} --env DB_PASSWORD=${DB_PASSWORD} --env EMAIL_PASS=${EMAIL_PASS} --env FILTER_EXCLUDE_KEYWORDS=${FILTER_EXCLUDE_KEYWORDS} -- npx -y [email protected]{
"mcpServers": {
"xiaohongshu-mcp-nodejs": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"CORS_CREDENTIALS": "${CORS_CREDENTIALS}",
"DB_PASSWORD": "${DB_PASSWORD}",
"EMAIL_PASS": "${EMAIL_PASS}",
"FILTER_EXCLUDE_KEYWORDS": "${FILTER_EXCLUDE_KEYWORDS}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
xiaohongshu-mcp | read | 小红书多账号管理MCP服务器 |
Trust audit
SAFEgrade B · trust 87/100 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 | PASS |
| 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
- declared (6 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (10)
const hash = crypto.createHash('md5');const hash = crypto.createHash('md5');const hash = crypto.createHash('md5');version: require('../../package.json').version,this.logDir = join(__dirname, '../../logs');
version: require('../../package.json').versionconst logger = require('../../utils/logger');version: require('../../../package.json').versionexpress, socket.io, playwright, playwright-extra, puppeteer-extra-plugin-stealth, ghost-cursor, mysql2, redis
Gates applied: no_behavioural_pass, no_license.
3795efa4b15efull audit observations/trust-audit/mcp-server/todieornot__xiaohongshu-4.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 |
|---|---|---|---|---|---|
| 2026-10-07 | 3795efa4b15e | SAFE | B | 87 | first audit |
Questions
What is the Xiaohongshu MCP server?
企业级小红书MCP Node.js重构 - 支持多账号矩阵管理、反风控、数据采集与发布
What tools does Xiaohongshu expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Xiaohongshu safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (87/100). 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 Xiaohongshu need?
It reads CORS_CREDENTIALS, DB_PASSWORD, EMAIL_PASS, FILTER_EXCLUDE_KEYWORDS, FILTER_KEYWORDS, KEYBOARD_RANDOMNESS, KEYBOARD_SIMULATION, KEYBOARD_SPEED, MCP_AUTH_ENABLED, MCP_AUTH_SECRET, MCP_TOKEN_EXPIRY and OSS_ACCESS_KEY_ID 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 current is this page?
The grade is for one exact copy of the source (3795efa4b15e), read on 2026-10-07. The repository is watched and re-audited when it changes.