Turn any web page into clean markdown for your agent.

Give the page reader a public URL and get the main content back as markdown or plain text, with the title, author, publish date, canonical URL and links pulled out. Navigation, cookie banners and scripts are stripped.

What you get back

• Main content as markdown (or text), picked from <main>, <article> or a cleaned body
• Metadata from meta tags, Open Graph and JSON-LD: title, description, author, publishedAt, siteName, lang, lead image
• Absolute, deduplicated links found in the content (up to 200)
• wordCount, truncated flag, final URL after redirects and HTTP status

Call it over HTTP

No account and no API key. The first response is 402 Payment Required with the price; an x402-capable client pays in USDC on Base and retries. You're only charged when the call succeeds.

curl -i -X POST https://api.exepal.com/v1/read \
  -H "content-type: application/json" \
  -d '{"url":"https://example.com/blog/post","format":"markdown"}'
# → 402 Payment Required (price, network: base, pay-to address)
# An x402 client pays in USDC and retries → 200 with the JSON answer

Use it from Claude, Cursor or any MCP client

Add https://api.exepal.com/mcp as a remote MCP server. The tools are read, read_batch, at the same price.

{
  "mcpServers": {
    "exepal": { "type": "http", "url": "https://api.exepal.com/mcp" }
  }
}

Questions

Does it render JavaScript?

No. It reads static HTML, text, markdown and JSON responses. Pages that only build their content in the browser come back thin.

Am I charged if the page fails to load?

No. If the site can't be reached, times out or answers 4xx/5xx you get a 502 with the reason and no payment settles.

Why not just fetch the page myself?

You can. The reader saves the tokens and parsing code: an agent gets a few kilobytes of clean markdown instead of 300 KB of HTML.

Related tools