RedNote MCP
The RedNote MCP server enables intelligent search and extraction of Xiaohongshu (Red Book) content.
Search Xiaohongshu Content: Execute keyword-based searches using the
queryparameterControl Result Count: Specify the number of results to return (default: 10)
Extract Rich Data: Retrieve structured information including:
Note titles and content
Author information
Interaction metrics (likes, favorites, comments)
Images (in WebP format)
Hashtags
Direct links to original notes
Handles Authentication: Automatically manages login state and session persistence
Efficient Processing: Utilizes parallel processing for concurrent content retrieval
Multiple Use Cases: Useful for content research, trend analysis, and data extraction
Enables searching and retrieving content from Xiaohongshu (Red Book) platform, including note titles, content, author information, interaction metrics, images, hashtags, and direct links.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@RedNote MCPsearch for skincare routines for sensitive skin"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
RedNote MCP - Xiaohongshu Content Search Tool
Overview
RedNote MCP is a Model Context Protocol (MCP) server for searching and retrieving content from Xiaohongshu (Red Book) platform. It provides intelligent content extraction with automatic login management and parallel processing capabilities.
Related MCP server: Stride28 Search MCP
Features
Smart Search: Keyword-based content search on Xiaohongshu
Auto Login: Automatic cookie management and login handling
Parallel Processing: Efficient concurrent content retrieval
Rich Data Extraction:
Note titles and content
Author information and descriptions
Interaction metrics (likes, favorites, comments)
Images and hashtags
Direct note links
Technical Stack
Runtime: Node.js with TypeScript
Browser Automation: Playwright
Protocol: Model Context Protocol (MCP) SDK
Validation: Zod schema validation
Package Manager: pnpm
Data Structure
interface RedBookNote {
title: string; // Note title
content: string; // Note content
author: string; // Author name
authorDesc?: string; // Author description
link: string; // Note URL
likes?: number; // Like count
collects?: number; // Favorite count
comments?: number; // Comment count
tags?: string[]; // Hashtag list
images?: string[]; // Image URLs (WebP format)
}Installation
Prerequisites
Node.js 18+
pnpm package manager
Setup
Clone the repository:
git clone <repository-url>
cd rednote-mcpInstall dependencies:
pnpm installInstall Playwright browsers:
pnpm exec playwright installBuild the project:
pnpm buildUsage
Running the MCP Server
pnpm startDevelopment Mode
pnpm devTesting
pnpm testMCP Client Configuration
Claude Desktop
Add the following configuration to your Claude Desktop config file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"rednote-mcp": {
"command": "node",
"args": [
"C:\\ABSOLUTE\\PATH\\TO\\rednote-mcp\\build\\index.js"
]
}
}
}For macOS/Linux users:
{
"mcpServers": {
"rednote-mcp": {
"command": "node",
"args": [
"/absolute/path/to/rednote-mcp/build/index.js"
]
}
}
}Replace the path with your actual project directory.
Other MCP Clients
For other MCP-compatible clients, use the built server file:
node build/index.jsTool Usage
Once configured, you can use the search tool in your MCP client:
Search for "food recommendation" on XiaohongshuThe tool will return structured data including titles, content, author information, and images.
Important Notes
First Run: Manual login to Xiaohongshu is required on first use
Performance: Initial searches may take 30-60 seconds due to browser startup and content loading
Rate Limiting: Concurrent requests are limited to 3 to avoid platform restrictions
Image Format: Images are provided in WebP format
Cookie Management: Login state is automatically saved and reused
Development
Project Structure
rednote-mcp/
├── src/
│ ├── index.ts # MCP server entry point
│ └── xiaohongshu.ts # Core scraping logic
├── cookies/ # Auto-generated cookie storage
├── results/ # Optional: saved search results
├── build/ # Compiled JavaScript output
├── package.json
├── tsconfig.json
└── README.mdAvailable Scripts
pnpm build- Build TypeScript to JavaScriptpnpm start- Run the built MCP serverpnpm dev- Development mode with auto-reloadpnpm test- Run tests (if available)pnpm clean- Clean build directory
Troubleshooting
Common Issues
Login Required: If you see login prompts, delete the
cookies/directory and restartTimeout Errors: Increase the MCP client timeout settings
Browser Not Found: Run
pnpm exec playwright installto install browsersPermission Errors: Ensure the project directory has proper read/write permissions
License
This project is licensed under the MIT License - see the LICENSE file for details.
Disclaimer
This tool is for educational and research purposes. Please respect Xiaohongshu's terms of service and rate limits when using this tool.
Available Tools
1 toolsearch_xiaohongshuC
Searches for content on Xiaohongshu (Red Note) based on a query
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of results to return | |
| query | Yes | Search query for Xiaohongshu content |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions searching but doesn't describe what type of content is returned, pagination behavior, rate limits, authentication requirements, or error conditions. This leaves significant gaps for a search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that communicates the core functionality without any wasted words. It's appropriately sized for a simple search tool and front-loads the essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with no annotations and no output schema, the description is insufficient. It doesn't explain what format results come in, what fields are returned, or any behavioral characteristics. The combination of missing annotations and minimal description creates significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 100% description coverage, clearly documenting both parameters. The description adds no additional parameter semantics beyond what's in the schema, so it meets the baseline for adequate but not exceptional parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Searches') and resource ('content on Xiaohongshu'), and includes the search mechanism ('based on a query'). However, with no sibling tools mentioned, there's no opportunity to demonstrate differentiation from alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or limitations. It merely restates the basic functionality without context about appropriate use cases or constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v1.0.0- First observed
search_xiaohongshu
TDQS
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and distinct by default.
A single tool inherently has consistent naming since there are no other tools to compare it against. The tool name follows a clear verb_noun pattern (search_xiaohongshu).
One tool is too few for a server named 'RedNote MCP' that implies broader functionality for interacting with Xiaohongshu. This feels thin and incomplete for the apparent scope, lacking basic operations like creating, updating, or retrieving specific content.
The tool surface is severely incomplete for a Xiaohongshu integration. It only provides search functionality, missing essential CRUD operations (e.g., create_post, get_post, update_post, delete_post) and other domain-specific actions like user interactions or analytics.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
搜索笔记、浏览首页推荐、查看笔记内容与评论,并发表你的评论。直接在工作流中与小红书内容互动,高效跟进话题。
XHS note/product search/detail, suggestions, comments/replies; PGY 20pts success, failures uncharged
Weibo hot search, post search/details, comments/replies, users, posts, transcript.
Get social media data from Instagram and TikTok: profiles, posts, videos, comments, and more.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables searching and accessing Xiaohongshu (RedNote) content via natural language, with cookie-based authentication for note retrieval and keyword search.1031,103MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to search real content from Xiaohongshu and Zhihu, supporting keyword search, note details, and question retrieval.84MIT
- AlicenseNot gradedqualityDmaintenanceEnables automated interaction and data scraping for Xiaohongshu (RedNote), including posting, liking, commenting, following, and retrieving user and note data.5MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to search and collect data from Xiaohongshu/REDnote, including notes, comments, and user info, with dual-layer anti-detection and persistent login.15-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MilesCool/rednote-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server