chenningling/redbook-search-comment-mcp2.0

This page was translated automatically. Technical details may differ from the original. View the original

458 stars 57 forks Quality 53 Trend 21

This is an automatic search and comment tool for Xiaohongshu developed based on Playwright. As an MCP Server, it can connect to MCP Clients (such as Claude for Desktop) through specific configurations, helping users automatically log in to Xiaohongshu, search keywords, retrieve note content, and post AI-generated comments.

Overview

This project is based on JonaFly/RednoteMCP and combined with multiple practical experiences, undergoing comprehensive optimization and feature expansion (by windsurf). Here, we sincerely thank the original authors for their contributions! This is an automatic search and comment tool for Xiaohongshu developed based on Playwright. As an MCP Server, it can connect to MCP Clients (such as Claude for Desktop) through specific configurations, helping users automatically log in to Xiaohongshu, search keywords, retrieve note content, and post AI-generated comments. - : Utilizes the large model capabilities of MCP clients (such as Claude) to generate more natural and relevant comment content - : Divides functions into three independent modules: note analysis, comment generation, and comment publishing to improve code maintainability - : Integrates multiple methods to obtain note content to ensure full access to the title, author, and body content of various notes - : Uses persistent browser context so no repeated login after first login - Retrieves note analysis results first, then the MCP client generates and publishes comments - : Refactored the note content retrieval module to increase page load wait times and scrolling operations, enabling four different content acquisition methods - : Restructured comment function to return note analysis results to the MCP client, allowing the client's AI capabilities to generate more natural and relevant comments - : Divided functions into three independent modules: note analysis, comment generation, and comment publishing to improve code maintainability - Solved the issue of note titles not displaying when searching, providing more complete search results - : Added more detailed error handling and debugging information output - :Supports manual QR code login; the status is saved after first login, so you don't need to scan again for subsequent use. -:Automatically detects login status and prompts users to log in when needed - : Supports multi-keyword search, allows specifying the number of returned results, and provides complete note information - : Integrates four different acquisition methods to ensure accurate access to note title, author, publication time, and body content - : Supports retrieving comment content for notes, including commenters, comment text, and time information - : Automatically analyzes note content, extracts key information, and identifies the field of the note - : Utilizes the AI capabilities of MCP clients (such as Claude) to generate natural, relevant comments based on note content - : Supports four different types of comments generation - : Guides users to follow or private messages - : Simple interactions to gain goodwill - : Increases interaction through questions - : Demonstrates professional knowledge and establishes authority - : Returns note analysis results in JSON format to the MCP client to facilitate AI-generated reviews - : Provides real-time feedback on review publication results

Overview (machine translated)

English | Chinese

This project is based on JonaFly/RednoteMCP and combined with multiple practical experiences, undergoing comprehensive optimization and feature expansion (by windsurf). Here, we sincerely thank the original authors for their contributions!

Main Features and Advantages

Deeply Integrated AI Capabilities: Leverage the large model capabilities of MCP clients (such as Claude) to generate more natural and relevant commentary content
Modular Design: Divides functions into three independent modules: note analysis, comment generation, and comment publishing, improving code maintainability
Powerful Content Acquisition Capability: Integrates multiple methods to obtain note content, ensuring complete access to the titles, authors, and body content of various notes
Persistent Login: Uses persistent browser context, so you don’t need to log in again after your first login
Two-step review process: First, obtain the note analysis results, then the MCP client generates and publishes the comments

Major optimizations in version 2.0

Content Acquisition Enhancement: Refactored the note content acquisition module, increasing page load wait times and scrolling operations, enabling four different content acquisition methods
AI Review Generation: Restructure the review feature by returning note analysis results to the MCP client, allowing the client’s AI capabilities to generate more natural and relevant comments
Functional Modularization: Divide functions into three independent modules: note analysis, comment generation, and comment publishing, improving code maintainability
Search Results Optimization: Fixed the issue where titles did not display when searching for notes, providing more complete search results
Enhanced Error Handling: Adds more detailed error handling and debugging information output

1. Core Features

Persistent Login: Supports manual QR code login; the status is saved after first login, and there is no need to scan again for subsequent use
Login Status Management: Automatically detects login status and prompts users to log in when needed

2. Content discovery and acquisition

Smart Keyword Search: Supports multi-keyword search, allows you to specify the number of returned results, and provides complete note information
Multi-dimensional Content Acquisition: Integrates four different acquisition methods to ensure accurate access to note titles, authors, publication dates, and body content
Comment Data Acquisition: Supports retrieving comments from notes, including commenters, comment text, and time information

3. Content analysis and generation

Note Content Analysis: Automatically analyzes note content, extracts key information, and identifies the field of the note
AI Review Generation: Utilizes the AI capabilities of MCP clients (such as Claude) to generate natural and relevant comments based on note content
Multi-type review support: Supports generating four different types of comments:
Traffic Generation: Guide users to follow or send private messages
Like Type: Simple interaction to gain goodwill
Consulting: Increase interaction through questions
Professional: Showcase professional knowledge to establish authority

This page was translated automatically. Technical details may differ from the original.

Install

This server does not publish a one-line install command.

Open the repository installation guide New to MCP? Start with the mcpskill.org guide →

Configuration

{
    "mcpServers": {
        "xiaohongshu MCP": {
            "command": "/绝对路径/到/venv/bin/python3",
            "args": [
                "/绝对路径/到/xiaohongshu_mcp.py",
                "--stdio"
            ]
        }
    }
}