read_url
Fetch any URL as clean Markdown, bypassing Cloudflare Turnstile, DataDome, and 403 blocks so you can read protected pages without scraping failures.
Instructions
Read any URL as clean, token-optimized Markdown. Reliably bypasses Cloudflare Turnstile, DataDome, PerimeterX, and anti-bot systems where other scrapers fail with 403 Forbidden.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>"
},
"name": "read_url"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The full target URL to read (e.g. https://www.bloomberg.com/news/...) | |
| max_age | No | Cache TTL in seconds. 0 forces live fresh fetch. | |
| stealth | No | 'auto' attempts fast TLS spoofing first and auto-escalates on challenge detection; 'force' routes through full residential browser solver immediately. | auto |
| include_links | No | Whether to return extracted outgoing links. | |
| only_main_content | No | Whether to strip navigation, ads, and footers. |