Fetch any URL and get clean Markdown. Optional JS rendering for SPAs. Built for RAG.
Fetch any public web page and get its main content back as clean, token-efficient Markdown — title, description, headings, links and lists. Optional JavaScript rendering handles SPAs and JS-heavy pages that would otherwise return empty. Ideal for RAG pipelines and agents that need to read a URL. Available over MCP and as a pay-per-call x402 HTTP endpoint (USDC on Base).
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/webmcp.json
{
"mcpServers": {
"web-scraper": {
"url": "https://api.agishub.com/mcp/web"
}
}
}x402 HTTP (pay-per-call)
curl -X POST https://api.agishub.com/paid/web-scraper \
-H "Content-Type: application/json" \
-d '{ "url": "https://example.com" }'
# → 402 Payment Required, then pay per call in USDC on Base (x402)| extract | Fetch a public URL and return its main content as clean Markdown. Optional render:true for JavaScript-heavy pages. |