hyperbrowser 3 tools

MCP server exposing 3 tools for hyperbrowser.

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/hyperbrowser/mcp
Content-Type: application/json

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

hyperbrowser_scrape — Scrape a single web page from a cloud browser and return clean content (markdown, html, links, and page metadata). Handles JS-rendered pages. Example: hyperbrowser_scrape({ url: "https://example.com", _apiKey: "your-key" })
hyperbrowser_extract — Extract structured JSON data from one or more web pages using an LLM. Provide a JSON schema and/or a natural-language prompt describing what to pull. Example: hyperbrowser_extract({ urls: ["https://example.com"], prompt: "Get the product name and price", schema: { type: "object", properties: { name: { type: "string" }, price: { type: "string" } } }, _apiKey: "your-key" })
hyperbrowser_crawl — Crawl a website starting from a URL, following links and scraping each page to markdown. Use maxPages to bound the crawl. Example: hyperbrowser_crawl({ url: "https://example.com", maxPages: 10, _apiKey: "your-key" })

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

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