extract_verified

online.x-402/mcp · Verify this server

Read a page and get a deterministic verdict on whether the retrieval can be trusted, with evidence. PRIVATE BETA. Verified browser-based web content retrieval for AI agents. Same retrieval as POST /v1/extract ($0.005), plus what an agent needs to trust the result without re-fetching it: declared block detection (HTTP status and blocking-page signatures), non-empty validation, content consistency checks against navigation-dominant and templated extractions, a retrieval timestamp, and evidence metadata including the final URL after redirects, character and word counts, and a sha256 checksum of the returned markdown. Every check is deterministic: no model runs in this path, so two calls on the same page return the same verification. Failed checks are DECLARED alongside the content, never hidden. This does not bypass CAPTCHA or authentication and makes no claim to defeat anti-bot systems: it detects blocking and says so. — $0.020012/call, paid per request via x402 (USDC). Use when asked: "read this page with proof", "was this page blocked", "verified page retrieval".