概要
What is Scraperis_scraper?
Scraperis_scraper is a Model Context Protocol (MCP) integration for Scraper.is—a web scraping tool that allows AI assistants to extract content from websites, capture screenshots, and retrieve data in multiple formats.
How to use Scraperis_scraper?
Install globally via npm or yarn, set the SCRAPERIS_API_KEY environment variable, then configure an MCP-compatible client (e.g., Claude Desktop) to use scraperis-mcp as a server. The AI assistant can then call the scrape tool to fetch web content.
Key features of Scraperis_scraper
- Web scraping of any public website
- Screenshot capture of web pages
- Output formats: markdown, HTML, JSON, and screenshot
- Real‑time progress updates during scraping
- Seamless MCP integration for AI assistants
Use cases of Scraperis_scraper
- Having an AI assistant summarize the latest news from a tech blog
- Extracting structured product data from e‑commerce sites
- Capturing screenshots of web pages for visual analysis
- Fetching up‑to‑date information from dynamic websites
FAQ from Scraperis_scraper
What dependencies are required to run Scraperis_scraper?
You need Node.js installed and a valid Scraper.is API key.
How do I get an API key?
Sign up or log in at scraper.is, go to the API Keys section in your dashboard, and create or copy an existing key.
Which AI assistants are compatible with Scraperis_scraper?
It works with any AI assistant that supports the Model Context Protocol (MCP), such as Claude Desktop.
Does Scraperis_scraper support multiple output formats?
Yes. The scrape tool can return content as markdown, HTML, JSON, a screenshot, or the “quick” format.
Is there any real‑time feedback during scraping?
Yes, the server provides real‑time progress updates during scrape operations.
