URL to Markdown - Clean Web Pages for LLMs & RAG

Give it a list of URLs and get clean Markdown back for each page - the ideal format for feeding web content to an LLM (retrieval-augmented generation), building a knowledge base, or saving to notes/docs.

Two modes:

• Main content (default) - runs Mozilla Readability first and converts just the article body, stripping nav, ads, sidebars and cookie banners. The cleanest possible LLM input.
• Full page - converts the whole page body (minus scripts, nav, header and footer).

Links and images are resolved to absolute URLs, tables are converted to Markdown tables (even header-less layout tables), and clutter attributes are stripped so nothing leaks as raw HTML. Pure HTTP + parsing, no browser, cents per page.

What you get per URL

title · markdown (the converted document) · mode · wordCount · charCount · url · status. Turn on YAML frontmatter to prepend a --- title / source / date --- block to each document.

Input

{
  "urls": ["https://en.wikipedia.org/wiki/Web_scraping"],
  "mode": "mainContent",
  "frontmatter": true
}

• URLs - one per line; a bare domain gets https://. Leave empty for a small free sample.
• Import URLs from a file - paste a list, or link a public .txt/.csv, a Google Sheet/Drive link, or an Apify key-value-store record.
• Output fields - tick only the columns you need (e.g. just url + markdown).

Notes

• Reads the server-rendered HTML. Pages rendered entirely client-side may convert to little content - use a proxy or a browser-based scraper for those.
• A URL that is unreachable or non-HTML is reported (status: "failed") and is not charged.

Use with AI assistants (MCP)

Available through the Apify MCP server - an agent can turn a list of links into clean Markdown context on demand for RAG or summarisation, with no page noise to confuse the model.

Agent-ready: autonomous payments (x402 & Skyfire)

This actor is agent-ready - AI agents can discover it, run it, and pay for it autonomously, with no Apify account and no human in the loop. It uses pay-per-event pricing and limited permissions, so it qualifies for Apify's agentic-payment standards:

• x402 - an open, HTTP-native payment protocol. Agents pay per run in USDC on the Base network directly through the Apify MCP server - no account, no API key.
• Skyfire - agent-to-service payments for fully autonomous AI-agent workflows.

Building an AI agent, MCP tool, or autonomous data pipeline? This scraper is ready to plug in and pay as it goes.