小红书MCP服务
@jobsonlook
基本情報
小红书MCP服务 について
小红书MCP服务 x-s x-t js逆向
概要
What is 小红书MCP服务?
小红书MCP服务 is an MCP (Model Context Protocol) server that enables AI assistants to interact with Xiaohongshu (Little Red Book) through HTTP APIs. It uses JavaScript reverse engineering to extract the required x-s and x-t parameters, avoiding the need for a full browser automation tool like Playwright. This service is intended for developers who want to integrate Xiaohongshu features into AI workflows.
How to use 小红书MCP服务?
To set up 小红书MCP服务, clone the repository and install dependencies using uv sync. Obtain your Xiaohongshu cookie by logging into the web version and copying it from the browser. Then configure the MCP server in your AI client’s settings (e.g., Claude Desktop) by providing the cookie as the XHS_COOKIE environment variable and running main.py via uv.
Key features of 小红书MCP服务
- Search for notes on Xiaohongshu
- Retrieve full note content
- Fetch comments on a note
- Post comments to a note
- Lightweight, no Playwright required
Use cases of 小红书MCP服务
- Search Xiaohongshu notes and extract content for analysis
- Gather user comments on specific posts
- Automatically respond or comment on notes (with responsibility)
- Integrate Xiaohongshu data into an AI assistant’s responses
FAQ from 小红书MCP服务
What operations does 小红书MCP服务 support?
It supports searching notes, retrieving note content, fetching comments, and posting comments.
What environment is required to run 小红书MCP服务?
You need Node.js, Python 3.12, and uv installed. Dependencies are managed with uv sync.
How do I get the Xiaohongshu cookie for authentication?
Log into the Xiaohongshu website (xiaohongshu.com) and extract your cookie from the browser’s developer tools. This cookie must be set as the XHS_COOKIE environment variable.
Is 小红书MCP服务 free to use?
The project is provided for learning and communication only. Any commercial use is prohibited, and users bear all risks.
How is the MCP server configured in my AI client?
Add an entry to your mcpServers JSON configuration with command: "uv", arguments pointing to the project directory and main.py, and the XHS_COOKIE environment variable.
「その他」の他のクライアント
Crowded Finance
mcp.crowdedfinance.comThe Crowded MCP allows organizations to run financial operations by asking — managing expenses, contacts, payment processing, reporting, and more. Samples of what you can do: Keep an eye on spending by asking "What sof
mcp-oi-wiki
shwstone🌟 Wiki of OI / ICPC for LLMs. （面向大模型的某大型游戏线上攻略，内含炫酷算术魔法）
Prove AI
preuve.aiStartup research engine. Scores ideas with live market data. Only 17.5% pass.
MCP 聊天应用
machaojin1917939763基于MCP(Model Context Protocol)的智能聊天应用，支持Web和桌面环境。集成OpenAI/Anthropic API，提供MCP服务器的所有工具能力。简洁现代的UI设计，支持跨平台部署。
FormLM
formlmBuild smart forms, scoring quizzes, and evaluation reports through natural language. An MCP Server that lets any AI agent create and manage complete assessment apps end-to-end.
コメント