MCP Smart Crawler
@loo-y
About MCP Smart Crawler
MCP Smart Crawler is a Model Context Protocol (MCP) server uses Playwright to crawl web content, extract metadata, and download resources such as videos and images.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-smart-crawler": {
"command": "npx",
"args": [
"-y",
"mcp-smart-crawler@latest",
"--download-folder",
"C:\\downloads"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is MCP Smart Crawler?
MCP Smart Crawler is a Model Context Protocol (MCP) server that uses Playwright to crawl web content, extract metadata, and download resources such as videos and images. It is designed for users who need to programmatically retrieve and save content from Xiaohongshu (小红书) share links.
How to use MCP Smart Crawler?
Configure your MCP client with the provided JSON, setting the command to npx and adding optional arguments like --download-folder to specify a local download directory. Then send a chat message containing a Xiaohongshu share link to trigger crawling and downloading.
Key features of MCP Smart Crawler
- Extracts metadata (title, description, images) from Xiaohongshu posts.
- Downloads videos and images from Xiaohongshu share links.
- Uses Playwright for browser automation.
- Configurable download folder via command-line argument.
Use cases of MCP Smart Crawler
- Automatically fetching and saving Xiaohongshu post images for content aggregation.
- Downloading videos from shared Xiaohongshu links for offline viewing.
- Extracting metadata from Xiaohongshu posts for analysis or archiving.
FAQ from MCP Smart Crawler
What does MCP Smart Crawler do?
It crawls web pages using Playwright, extracts metadata like title and images from Xiaohongshu posts, and downloads associated videos and images.
What dependencies does MCP Smart Crawler require?
It requires Playwright for browser automation, and is run via npx (Node.js package runner). No other runtime dependencies are specified.
Where are downloaded files saved?
Files are saved to the local folder specified by the --download-folder argument. If not provided, the default behavior is not documented.
Does MCP Smart Crawler support authentication or transport security?
No authentication or transport security mechanisms are mentioned in the README.
Can MCP Smart Crawler work with websites other than Xiaohongshu?
The README only describes functionality for Xiaohongshu share links; no other websites are mentioned.
More Browser Automation MCP servers
MCP Browser Kit
ndthanhdevAn MCP Server that enables AI assistants to interact with your local browsers.
Webpage Screenshot MCP Server
ananddtyagiAn MCP that gives your agent the ability to snap a screenshot of webpages. Useful when you want your agent to check its progress during development.
Fetcher MCP
jae-jaeMCP server for fetch web page content using Playwright headless browser.
fetch-mcp
egoistAn MCP server for fetching URLs / Youtube video transcript.
Fetch MCP
jae-jaeMCP server for fetch web page content using Playwright headless browser.
Comments