For AI agents
Dr Urls speaks Model Context Protocol. An assistant can list your sites, read an audit, find issues, start a scan, and — when the answer needs a person rather than a crawler — hire one.
Connect
{
"mcpServers": {
"drurls": {
"url": "https://drurls.com/api/v1/mcp",
"headers": { "Authorization": "Bearer <your-api-key>" }
}
}
}Mint a key in the dashboard. Full tool list on the MCP page.
Two ways to pay
With an account — tools draw on your credit balance, exactly as the web app does. Pay-per-call from a wallet (x402) is built but deliberately off until settlement works end to end — do not send X-PAYMENT headers yet; an unauthenticated call to a paid tool answers 401 telling you how to get a key. Meanwhile, free_page_check works with no credentials at all.
What things cost
Reading is free: listing sites, reading a report, searching issues and checking scan status only surface data you already paid to produce. Work costs credits — included with a plan, or bought as top-ups.
| Action | Credits |
|---|---|
| Scans | 1 |
| AI reviews | 2 |
| Tester orders | 1 |
Hiring a tester is priced by the offer, not by the action — see the tester catalogue. Machine-readable prices: /pricing.md.
When to hire a person instead
An audit measures what is measurable. It cannot tell you whether a layout is broken on a real phone, whether a checkout confuses people, or what a screen reader actually announces. For those, hire_tester buys a real person on a real device, who returns a recorded walkthrough with a screenshot and the console output of every step.