Fetch public webpages through SSRF guardrails and return clean markdown extraction plus prompt-injection risk signals before an agent summarizes, reasons, or calls another tool.
/v1/safe-fetch-url
/x402/v1/safe-fetch-url
safe_fetch_url
Scan untrusted text for instruction override, exfiltration, and agent-manipulation patterns before placing that text into an AI agent context.
/v1/check-prompt-injection-risk
/x402/v1/check-prompt-injection-risk
check_prompt_injection_risk
Check whether a public source supports, contradicts, or does not address a claim before an agent cites it or relies on it.
/v1/verify-claim-against-source
/x402/v1/verify-claim-against-source
verify_claim_against_source
Capture timestamped page metadata, content hashes, and optional screenshot or text artifacts before an agent acts on a price, policy, availability, or source page.
/v1/create-page-proof
/x402/v1/create-page-proof
create_page_proof
Extract return windows, free-return signals, restocking fees, refund methods, exchange terms, warranty signals, snippets, and confidence from a public merchant page.
/v1/extract-return-policy
/x402/v1/extract-return-policy
extract_return_policy
Extract structured subscription, trial, renewal, billing, cancellation, refund, commitment, notice, and price-change signals from a public subscription page.
/v1/extract-subscription-terms
/x402/v1/extract-subscription-terms
extract_subscription_terms
Check whether a public product page appears to fit buyer constraints before an agent recommends, shortlists, compares, or purchases it.
/v1/check-product-fit
/x402/v1/check-product-fit
check_product_fit
Understand how Primitive402 exposes paid APIs for AI agents through HTTP 402 Payment Required and Base Sepolia testnet USDC during public beta.
/docs/x402
/docs/x402/paid-test
/x402/catalog.json