$ loading_
Politely scrape websites and extract structured data with bounded async crawling.
This appears to be an open-source, local Scrapy-based MCP scraping server with no required secrets and no declared fixed third-party SaaS endpoint. Its main exposure comes from normal local code execution and outbound requests to target websites; based on the available materials, it fits caution rather than high risk.
The materials explicitly state that no keys or environment variables are required, and there is no sign of API tokens, account credentials, or cloud secrets being requested, so credential exposure and abuse risk appears low.
Although no fixed remote endpoint is declared, the tool’s core purpose is web fetching, sitemap/robots.txt reading, and bounded asynchronous crawling, so it will make outbound requests to user-specified websites and has the normal exposure of network egress and interaction with target sites.
The system flags executes-code; as a Scrapy-based MCP server, it needs to run scraping logic/processes locally. This is a normal capability for this class of tool, and the materials do not show additional red flags such as unusually broad system permissions.
From the description, the tool accesses remote web content and extracts links, tables, and CSS/XPath results, so it may process data returned from user-specified crawl targets. The materials do not indicate broad local file permissions or data access demands that exceed its stated purpose.
Positive signals are that it is open source under the MIT License and the source is auditable; however, it comes from a third-party registry, has 0 stars, unknown maintenance status, and no README, which reduces verifiability and maturity, so supply-chain caution is warranted.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "scrapy-mcp" yet — see the docs or source repo.
Fetch this e-commerce category page, use CSS selectors to extract each product's name, price, rating, and detail-page link, and return structured JSON.
A JSON array of products with key fields, ready for analysis or storage.
Read the target website's sitemap.xml and robots.txt, summarize crawlable areas and blocked paths, and list the main URL groups found in the sitemap.
A summary of crawling rules and a categorized list of URLs.
Start from the blog homepage, crawl up to 50 pages with a maximum depth of 2, and extract each article's title, publish date, author, and content summary.
A bounded crawl result with article summaries, avoiding uncontrolled crawling.
Scrape web pages in bulk with selectors, stealth mode, and automation.
Crawl pages and extract web data with Selenium, pagination, scrolling, and screenshots.
Scrape static HTML pages and extract structured content for AI analysis.
Fetch web pages and APIs with custom headers, methods, redirects, and timeouts.
Scrape websites, crawl deeply, and automate structured research extraction.
Extract clean web content, links, structured elements, and search the web.