Xiaohongshu XHS RedNote MCP

Xiaohongshu XHS RedNote MCP

Read-only MCP bridge for Xiaohongshu / XHS / RedNote social media insights: search notes, get note details and comments, creator profiles, and creator note lists.

Category
访问服务器

README

小红书 MCP | Xiaohongshu MCP | XHS MCP | RedNote MCP

This public repository provides a minimal MCP bridge plus public connection docs for a hosted 小红书 MCP / Xiaohongshu MCP / XHS MCP / RedNote MCP service.

If you are looking for a 小红书 MCP, Xiaohongshu MCP, XHS MCP, or RedNote MCP for social media research workflows, this repository includes:

  • a minimal local stdio bridge for MCP clients and Glama inspection
  • public MCP metadata and client configuration examples
  • the direct hosted streamable-http endpoint for clients that already support remote MCP

The business implementation is privately hosted. This repository exposes only the public connection surface for read-only social media intelligence workflows.

Search Aliases

Common search phrases for this MCP service:

  • 小红书 MCP
  • 小红书 XHS MCP
  • Xiaohongshu MCP
  • XHS MCP
  • RedNote MCP
  • Xiaohongshu note search MCP

Service

  • Hosted upstream MCP endpoint: https://mcp.52choujiang.com/xhs/mcp
  • Hosted upstream transport: streamable-http
  • Authentication: Authorization: Bearer <XHS_MCP_API_KEY>
  • Website: https://52choujiang.com/assistant
  • Registry name: com.52choujiang/xhs-insights
  • Current public capability version: 0.1.3

Bridge

This repository also ships a minimal local stdio bridge. It forwards MCP requests to the hosted upstream service and keeps the public repo runnable for Glama server inspection and MCP clients that prefer command-based servers.

The bridge does not contain the private service implementation. It only relays MCP traffic to the hosted endpoint.

Bridge Environment

  • XHS_MCP_API_KEY Required for authenticated tool calls. Discovery methods such as initialize and tools/list can still be inspected without a key.
  • XHS_MCP_UPSTREAM_URL Optional override for the hosted upstream URL. Default: https://mcp.52choujiang.com/xhs/mcp

Local Run

npm install
XHS_MCP_API_KEY="<XHS_MCP_API_KEY>" npm start

Docker Run

docker build -t xhs-mcp-bridge .
docker run --rm -i -e XHS_MCP_API_KEY="<XHS_MCP_API_KEY>" xhs-mcp-bridge

If Docker Hub is slow from your network, keep the default image unchanged for normal use and override only during local builds:

docker build --build-arg NODE_IMAGE=mirror.gcr.io/library/node:20-alpine -t xhs-mcp-bridge .

Read-Only Scope

This MCP service is designed for read-only social media intelligence workflows. It does not provide account login, posting, editing, liking, commenting, or other account actions.

Supported workflows include:

  • Search related Xiaohongshu notes by keyword.
  • Resolve a shared note link or share text into structured note details.
  • Read note details when the caller already has a note ID.
  • Fetch paginated first-level comments for comment analysis.
  • Read creator profile data from a profile link or user ID.
  • Fetch paginated creator note lists for content style and account research.

Tools

Tool Public purpose
xhs_search_notes Search Xiaohongshu / 小红书 notes by keyword for research and discovery.
xhs_get_note_detail_by_note_url Resolve a shared XHS link or share text into structured note details.
xhs_get_note_detail_by_note_id Fetch structured note details when the caller already has a note ID.
xhs_get_note_comments_by_note_id Fetch paginated first-level comments when the caller already has a note ID.
xhs_get_note_comments_by_note_url Fetch paginated first-level comments directly from a shared note URL or share text.
xhs_get_user_info_by_user_id Fetch creator profile data when the caller already has a user ID.
xhs_get_user_info_by_profile_url Resolve a profile link or share text into creator profile data.
xhs_get_user_posted_notes_by_user_id Fetch a paginated list of notes published by a creator when the caller already has a user ID.
xhs_get_user_posted_notes_by_profile_url Fetch a paginated list of notes published by a creator from a profile link or share text.

Quick Start

For command-based MCP clients, use the local bridge published by this repository:

{
  "mcpServers": {
    "xiaohongshu-xhs-rednote-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "github:DevinChen2014/xiaohongshu-xhs-rednote-mcp"
      ],
      "env": {
        "XHS_MCP_API_KEY": "<XHS_MCP_API_KEY>"
      }
    }
  }
}

For clients that already support authenticated streamable-http, use the hosted upstream endpoint directly. A ready-to-copy example is available in examples/streamable_http_config.json.

Client Examples

Configuration examples are available in examples:

API Key

Request or manage API access from the product website:

https://52choujiang.com/assistant

Use the key as a Bearer token in the Authorization request header. Do not commit real API keys to code, docs, issues, or screenshots.

Directory Metadata

Public metadata files in this repository:

License

The files in this public repository are released under the MIT License. The license covers the public bridge wrapper, documentation, and configuration examples in this repository only. It does not cover the managed service implementation, hosted infrastructure, or any private backend code outside this repository.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选