What it does
The server reads any single page or an entire site and returns clean Markdown or JSON. It can also return site maps and extract fields that the user describes in plain words. It is one of three hosted MCP servers that the publisher offers on Apify; the other two cover app store reviews and Google Play search with SERP rank checks.
It suits pipelines that feed web content into AI agents or retrieval-augmented generation, where pages need to be converted into clean text or structured data before use.
Nothing is installed locally. An MCP client such as Claude Desktop, Cursor or another compatible client connects over Streamable HTTP using an Apify API token. Each tool states its cost before it runs, failed calls are not charged, and prices are listed on the Apify Store page. Apify's free plan includes a monthly credit for trying the tools. Questions can be raised as an issue on the Store page.
Limitations and requirements
Requires an Apify API token and an Apify account. Usage is pay per use, with prices shown on the Store page.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Web Scraper & Crawler for RAG (Markdown)
Website to clean Markdown or JSON for AI and RAG: read pages, crawl sites, extract described fields.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it