About 小红书MCP服务器 | xhs-mcp-server
A MCP server built on Electron and Xiaohongshu's web API, giving AI assistants access to notes, comments and user data. It is set up through a browser extension and needs no complex configuration.
Key features
- 01Ten built-in MCP tools
- 02Data retrieval through web API calls
- 03StreamableHTTP connection support
- 04Customizable authentication headers
- 05Settings import from configuration files
Use cases
- 01Collecting Xiaohongshu notes and comments for AI assistants
- 02Supporting account operations with data analysis
- 03Exporting retrieved data for organization
MCP support
The project runs as an MCP server that exposes 10 tools to AI clients over the StreamableHTTP protocol.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README小红书 MCP 服务器
简单、快速、精准的小红书 MCP 服务，方便接入 AI 助手实现自动化运营。
优势
- 简单 - 无需复杂配置，浏览器 + 插件即可，2 分钟搞定
- 精准 - 纯接口调用，数据比传统抓取更齐全、精准
- 快速 - 数据量不大时，1-2 秒完成执行
功能一览
内置 10 个 MCP 工具，支持扩展开发。
AI 客户端使用 StreamableHTTP 协议连接 MCP 服务，可自定义认证头增强安全性。
快速运行（无需安装）
- 打开 小红书官网
- 按
F12或Ctrl+Shift+J打开控制台 - 粘贴以下代码并回车：
fetch('//raw.githubusercontent.com/aicu-icu/xhs-mcp-server/refs/heads/main/loader.user.js').then(r=>r.text()).then(eval)
✅ 如果页面右下角显示了 Broxy 图标，则执行成功。关闭控制台后点击图标启动即可。
⚠️ 关闭页面后失效。
快速安装
- 安装 Broxy 扩展：https://broxy.dev
- 安装完毕后，打开小红书网页：https://www.xiaohongshu.com
- 点击右下角的 Broxy 图标，进入设置，【从链接导入数据】，地址填写：
https://cdn.jsdelivr.net/gh/aicu-icu/xhs-mcp-server@main/data-json/latest.json - 或者下载当前项目目录的
data-json/下的配置文件，然后在 Broxy 扩展里从文件导入
导入完毕，点击启动，即可获取 MCP 服务地址去使用
注意事项
小红书接口请求频繁或
xsec_token参数不匹配会触发风控，导致账号异常退出。 请避免 AI 助手调用过于频繁，不要编造不存在的笔记/用户 ID 或xsec_token。
联系我们
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.