Xiaohongshu (Little Red Book) MCP Server

io.github.shanyang-mePublished by GitHub account shanyang-mev0.1.1Updated Oct 24, 2026

Publish, search, and manage Xiaohongshu (Little Red Book) content via MCP tools.

VerifiedSTDIODesktop onlyBrowser AutomationCommunication & Collaboration

Overview

AI-generated overview

A local MCP server that lets an AI assistant publish, search and manage Xiaohongshu (Little Red Book) content through a headless browser session.

What you can do
Log in to Xiaohongshu by QR code, check login status, poll scan status and reload saved cookies from disk. Publish image notes with a title, text, images and tags. Search notes by keyword and read full details of a note. Look up user profile information.
When to use it
Useful when you want an assistant to draft and publish Xiaohongshu posts, research notes on a topic, or check account and note details without opening the app manually.
Requirements
Runs locally as a Python package (Python 3.12+) over stdio or HTTP; Chromium must be installed via Playwright. A Xiaohongshu account is required, logged in by scanning a QR code; session cookies are saved to a local file. Optional extra package for QR code images.
Before you install
Publishing posts is a public, hard-to-undo action on a real social account. Session cookies are stored on disk and grant account access. The server drives Xiaohongshu's internal API through a headless browser to bypass anti-bot detection, which may conflict with the platform's terms and risk account restrictions.

Installation

In SourceWeft

  1. Open Xiaohongshu (Little Red Book) MCP Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

xiaohongshu-mcp-server

A Model Context Protocol (MCP) server for Xiaohongshu (Little Red Book) - China's leading lifestyle social media platform.

Publish image notes, search content, view note details, and manage your account - all through MCP tools that AI assistants can use directly.

How It Works

Uses Playwright to run a headless Chromium browser that:

  1. Loads your XHS session cookies
  2. Generates authentic API signatures via the XHS web app's built-in signing function
  3. Makes API calls through the browser's network context (bypasses anti-bot detection)
  4. Uploads images directly to XHS CDN

No browser automation of UI elements - all interactions go through XHS's internal API.

Tools

ToolDescription
check_login_statusCheck if you're logged in
get_login_qrcodeGenerate QR code for login
check_qrcode_statusPoll QR scan status & save session
reload_cookiesReload cookies from disk
publish_contentPublish an image note with title, text, images, and tags
search_feedsSearch XHS notes by keyword
get_feed_detailGet full details of a note
user_profileGet user profile information

Installation

bash
pip install xiaohongshu-mcp-serverplaywright install chromium

For QR code image generation (optional):

bash
pip install "xiaohongshu-mcp[qrcode]"

Quick Start

1. Start the server

HTTP mode (for Claude Code, Cursor, etc.):

bash
xhs-mcp --transport http --port 18060

stdio mode (for Claude Desktop):

bash
xhs-mcp --transport stdio

2. Login

Call the get_login_qrcode tool, scan the QR code with the Xiaohongshu app, then call check_qrcode_status with the returned qr_id and code. Cookies are saved to ~/.xhs-mcp/cookies.json and persist across restarts.

3. Use

Ask your AI assistant to publish a note, search for content, etc.

Configuration

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

json
{  "mcpServers": {    "xhs-mcp": {      "command": "xhs-mcp",      "args": ["--transport", "stdio"]    }  }}

Claude Code

bash
claude mcp add xhs-mcp --transport http http://localhost:18060/mcp

Then start the server: xhs-mcp

As a LaunchAgent (macOS auto-start)

Create ~/Library/LaunchAgents/com.xhs-mcp.plist:

xml
<?xml version="1.0" encoding="UTF-8"?><!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd"><plist version="1.0"><dict>    <key>Label</key>    <string>com.xhs-mcp</string>    <key>ProgramArguments</key>    <array>        <string>/path/to/your/venv/bin/xhs-mcp</string>    </array>    <key>RunAtLoad</key>    <true/>    <key>KeepAlive</key>    <true/>    <key>StandardOutPath</key>    <string>/tmp/xhs-mcp.log</string>    <key>StandardErrorPath</key>    <string>/tmp/xhs-mcp.err</string></dict></plist>
bash
launchctl load ~/Library/LaunchAgents/com.xhs-mcp.plist

Example: Publish a Note

python
# Via MCP tool callpublish_content(    title="Hello XHS!",    content="My first post published via MCP.",    images=["/path/to/photo.jpg"],    tags=["MCP", "AI"])

Requirements

  • Python 3.12+
  • Chromium (installed via playwright install chromium)
  • A Xiaohongshu account

License

MIT

Source: README.md at commit e4fb862

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts