← Back to Skills Marketplace
borye

Xiaohongshu (小红书) Automation

by Borye · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
38549
Downloads
188
Stars
316
Active Installs
1
Versions
Install in OpenClaw
/install xiaohongshu-mcp
Description
Automate Xiaohongshu (RedNote) content operations using a Python client for the xiaohongshu-mcp server. Use for: (1) Publishing image, text, and video content, (2) Searching for notes and trends, (3) Analyzing post details and comments, (4) Managing user profiles and content feeds. Triggers: xiaohongshu automation, rednote content, publish to xiaohongshu, xiaohongshu search, social media management.
README (SKILL.md)

Xiaohongshu MCP Skill (with Python Client)

Automate content operations on Xiaohongshu (小红书) using a bundled Python script that interacts with the xpzouying/xiaohongshu-mcp server (8.4k+ stars).

Project: xpzouying/xiaohongshu-mcp

1. Local Server Setup

This skill requires the xiaohongshu-mcp server to be running on your local machine.

Step 1: Download Binaries

Download the appropriate binaries for your system from the GitHub Releases page.

Platform MCP Server Login Tool
macOS (Apple Silicon) xiaohongshu-mcp-darwin-arm64 xiaohongshu-login-darwin-arm64
macOS (Intel) xiaohongshu-mcp-darwin-amd64 xiaohongshu-login-darwin-amd64
Windows xiaohongshu-mcp-windows-amd64.exe xiaohongshu-login-windows-amd64.exe
Linux xiaohongshu-mcp-linux-amd64 xiaohongshu-login-linux-amd64

Grant execute permission to the downloaded files:

chmod +x xiaohongshu-mcp-darwin-arm64 xiaohongshu-login-darwin-arm64

Step 2: Login (First Time Only)

Run the login tool. It will open a browser window with a QR code. Scan it with your Xiaohongshu mobile app.

./xiaohongshu-login-darwin-arm64

Important: Do not log into the same Xiaohongshu account on any other web browser, as this will invalidate the server's session.

Step 3: Start the MCP Server

Run the MCP server in a separate terminal window. It will run in the background.

# Run in headless mode (recommended)
./xiaohongshu-mcp-darwin-arm64

# Or, run with a visible browser for debugging
./xiaohongshu-mcp-darwin-arm64 -headless=false

The server will be available at http://localhost:18060.

2. Using the Skill

This skill includes a Python client (scripts/xhs_client.py) to interact with the local server. You can use it directly from the shell.

Available Commands

Command Description Example
status Check login status python scripts/xhs_client.py status
search \x3Ckeyword> Search for notes python scripts/xhs_client.py search "咖啡"
detail \x3Cid> \x3Ctoken> Get note details python scripts/xhs_client.py detail "note_id" "xsec_token"
feeds Get recommended feed python scripts/xhs_client.py feeds
publish \x3Ctitle> \x3Ccontent> \x3Cimages> Publish a note python scripts/xhs_client.py publish "Title" "Content" "url1,url2"

Example Workflow: Market Research

  1. Check Status: First, ensure the server is running and you are logged in.

    python ~/clawd/skills/xiaohongshu-mcp/scripts/xhs_client.py status
    
  2. Search for a Keyword: Find notes related to your research topic. The output will include the feed_id and xsec_token needed for the next step.

    python ~/clawd/skills/xiaohongshu-mcp/scripts/xhs_client.py search "户外电源"
    
  3. Get Note Details: Use the feed_id and xsec_token from the search results to get the full content and comments of a specific note.

    python ~/clawd/skills/xiaohongshu-mcp/scripts/xhs_client.py detail "64f1a2b3c4d5e6f7a8b9c0d1" "security_token_here"
    
  4. Analyze: Review the note's content, comments, and engagement data to gather insights.

Usage Guidance
Install only if you trust the upstream xiaohongshu-mcp binaries and are comfortable giving a local service access to your Xiaohongshu account. Verify releases where possible, use a low-risk account, stop the server when not in use, and manually review every title, body, image URL, and tag before running the publish command.
Capability Analysis
Type: OpenClaw Skill Name: xiaohongshu-mcp Version: 1.0.0 The skill is classified as suspicious due to its reliance on external, third-party binaries for core functionality. The `SKILL.md` explicitly instructs the user to download and execute `xiaohongshu-mcp` and `xiaohongshu-login` binaries from a GitHub repository, which then run a local server. While the bundled Python client (`scripts/xhs_client.py`) only communicates with this local server (`http://localhost:18060`) and does not exhibit direct malicious behavior (e.g., data exfiltration, remote execution), the requirement to run untrusted external executables introduces a significant supply chain risk and places a high trust burden on the user for a component outside the skill bundle's direct control.
Capability Assessment
Purpose & Capability
The purpose matches the artifacts: search, read details, feeds, and publish Xiaohongshu content through a local server. The concern is that publishing is a high-impact, public account action and the client sends it directly to the publish endpoint.
Instruction Scope
The documentation discloses the commands and localhost server, but it does not require a preview, dry run, or explicit confirmation before posting live content. The trigger phrase 'social media management' is also broader than Xiaohongshu-specific use.
Install Mechanism
Setup instructs users to download, chmod, and run external GitHub release binaries for login and server operation without a pinned version, checksum, or signature verification in the skill artifacts.
Credentials
An authenticated Xiaohongshu session is expected for the skill's purpose, but it gives the local server account-level authority including posting and reading account-related/feed data.
Persistence & Privilege
The server is intentionally run as a local background service on localhost:18060. This is disclosed, but users need to stop it when finished because it remains tied to the authenticated session.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install xiaohongshu-mcp
  3. After installation, invoke the skill by name or use /xiaohongshu-mcp
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of xiaohongshu-mcp skill. - Automate Xiaohongshu (RedNote) content operations via Python client for the xiaohongshu-mcp local server. - Supports publishing image, text, and video content to Xiaohongshu. - Enables searching for notes and trending topics, analyzing post details and comments, and managing user feeds and profiles. - Provides clear setup instructions for running the required local server and login steps. - Includes CLI Python script with commands for status checks, searching, publishing, and retrieving detailed note information.
Metadata
Slug xiaohongshu-mcp
Version 1.0.0
License
All-time Installs 337
Active Installs 316
Total Versions 1
Frequently Asked Questions

What is Xiaohongshu (小红书) Automation?

Automate Xiaohongshu (RedNote) content operations using a Python client for the xiaohongshu-mcp server. Use for: (1) Publishing image, text, and video content, (2) Searching for notes and trends, (3) Analyzing post details and comments, (4) Managing user profiles and content feeds. Triggers: xiaohongshu automation, rednote content, publish to xiaohongshu, xiaohongshu search, social media management. It is an AI Agent Skill for Claude Code / OpenClaw, with 38549 downloads so far.

How do I install Xiaohongshu (小红书) Automation?

Run "/install xiaohongshu-mcp" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Xiaohongshu (小红书) Automation free?

Yes, Xiaohongshu (小红书) Automation is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Xiaohongshu (小红书) Automation support?

Xiaohongshu (小红书) Automation is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Xiaohongshu (小红书) Automation?

It is built and maintained by Borye (@borye); the current version is v1.0.0.

💬 Comments