scrapingant 3 tools

MCP server exposing 3 tools for scrapingant.

Endpoint

This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.

POST https://gateway.pipeworx.io/scrapingant/mcp
Content-Type: application/json

{"jsonrpc":"2.0","id":1,"method":"tools/list"}

Tools

• scrapingant_scrape — Scrape a web page and return its raw HTML via ScrapingAnt (headless-browser rendering + rotating proxies). Handles JS-heavy sites and anti-bot pages. Example: scrapingant_scrape({ url: "https://example.com", browser: true, _apiKey: "your-key" })
• scrapingant_markdown — Fetch a web page and return clean, LLM-ready Markdown (boilerplate stripped) via ScrapingAnt. Ideal for feeding page content to a model. Example: scrapingant_markdown({ url: "https://example.com/article", _apiKey: "your-key" })
• scrapingant_extract — Extract structured data from a web page using ScrapingAnt AI extraction. Describe the fields you want in `extract_properties` (comma-separated) and get back a JSON object with matching camelCase keys. Example: scrapingant_extract({ url: "https://example.com/product", extract_properties: "product title, price(number), full description", _apiKey: "your-key" })

Full documentation

Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/scrapingant/

About Pipeworx

Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io