Agis Web Scraper

Read any URL as Markdown, scrape by selector, extract structured JSON with AI, snapshot & list links. Built for RAG.

Web & DataMCP + x402from $0.002 Live

Overview

A full web-reading toolkit for agents. Fetch any public page as clean, token-efficient Markdown, or go further: scrape specific elements by CSS selector, list every link, capture a page snapshot (HTML + screenshot + markdown), and run AI-powered structured extraction that turns a URL and a prompt into clean JSON. JavaScript rendering handles SPAs and JS-heavy pages. Ideal for RAG pipelines and agents that need to read, parse or extract from the web. The free reader is available over MCP; the browser-powered actions are pay-per-call x402 HTTP endpoints (USDC on Base).

Connect it

Add the remote MCP server to any client, or call the x402 HTTP endpoint directly.

Claude / Cursor / Windsurf

claude mcp add --transport http web-scraper https://api.agishub.com/mcp/web

mcp.json

{
  "mcpServers": {
    "web-scraper": {
      "url": "https://api.agishub.com/mcp/web"
    }
  }
}

x402 HTTP (pay-per-call)

curl -X POST https://api.agishub.com/paid/extract-json \
  -H "Content-Type: application/json" \
  -d '{ "url": "https://example.com", "prompt": "the product name and price" }'
# → 402 Payment Required, then pay per call in USDC on Base (x402)

Tools included5

extract	Fetch a public URL and return its main content as clean Markdown. Optional render:true for JavaScript-heavy pages.
scrape	Extract specific elements from a JS-rendered page by CSS selector — text and attributes of every match.
structured	AI-powered structured extraction: a URL plus a prompt and/or JSON Schema returns clean structured JSON.
snapshot	Capture several representations of a page in one call — rendered HTML, a PNG screenshot, and optional Markdown / accessibility tree.
links	Return every hyperlink on a JS-rendered page as absolute URLs, with visible-only and same-site filters.