FabTally WebSafe · read-only · stateless · best-effort

Screen the web before
your agent touches it.

Three checks an AI agent runs before it fetches an arbitrary URL or ingests untrusted content — screen a URL for SSRF (private / loopback / cloud-metadata targets), TLS and redirect risk before fetching it (also a webhook verifier); scan text or a page for prompt-injection and hidden text; and resolve robots.txt / llms.txt / ai.txt to an allow/deny for your crawler. Read-only, keyless, nothing stored. Paid per call in USDC on Base via x402 or a prepaid credit key. Also a standalone MCP server.

Paid per call — $0.001 to $0.004.
Agents pay per call in USDC on Base via x402 (no account — an unpaid call returns a signed 402 challenge to pay-and-retry). Humans can prepay by card and send an X-FabTally-Key: fabt_… header instead. Bad input → 400, never charged. Every check has a rate-limited free teaser (this page uses them).
Buy prepaid credits →

The three checks

Use it from an agent

HTTP (x402) — POST any check as JSON: curl -XPOST https://websafe.fabtally.com/v1/url-safety \ -d '{"url":"http://169.254.169.254/latest/meta-data/"}' → 402 with a signed x402 challenge; pay in USDC on Base and retry with the X-PAYMENT header. Prepaid credit — add X-FabTally-Key: fabt_… to charge a card-funded balance instead. MCP server — streamable-http: https://websafe.fabtally.com/mcp · also stdio (npm: fabtally-websafe-mcp). 3 tools (url_safety, injection_scan, robots_check); paid tools relay the x402 challenge to pay-and-retry. Discovery/agent/overview · /openapi.json · /.well-known/x402