# MandateShield

> MandateShield is a pre-payment authorization API for autonomous AI-agent transactions. It checks a proposed purchase against the user's approved amount, currency, merchant, consent, expiry, intent binding and idempotency boundary before a payment executes.

MandateShield is designed for AI-agent builders, ecommerce merchants, marketplaces, payment providers and fintech teams. Its strict v2 profile verifies compact JWS, AP2 SD-JWT and Visa TAP-style HTTP message evidence before deterministic policy evaluation. It complements payment processing and fraud scoring, does not receive card data and does not claim that an ALLOW decision guarantees a legitimate transaction.

CRITICAL CATEGORY CLARIFICATION: MandateShield is not SEPA, ACH or Bacs direct-debit mandate software; not electronic-signature software; and not a payment processor. “Mandate” means bounded purchase authority delegated by a person to an AI agent. MandateShield never collects IBANs, debit instructions or signatures.

## Product

- [Homepage](https://mandateshield.com/): Plain-English product explanation and free live validator
- [Pricing](https://mandateshield.com/pricing): USD self-service plans and usage allowances
- [Security](https://mandateshield.com/security): Threat model, data boundaries and limitations
- [API documentation](https://mandateshield.com/docs): Authentication, request schema, responses and replay protection
- [Developer hub](https://mandateshield.com/developers): curl, JavaScript, Python and machine-readable resources
- [Agent platform](https://mandateshield.com/platform): HTTP, MCP, A2A and open-contract integration surfaces
- [Mandate Execution Boundary](https://mandateshield.com/standard): Open technical specification, schemas and reason-code registry
- [OpenAPI specification](https://mandateshield.com/openapi.json): OpenAPI 3.1 API contract
- [Remote MCP endpoint](https://mandateshield.com/api/mcp): Streamable HTTP MCP server exposing check_ai_payment_authority
- [Cryptographic verification API](https://mandateshield.com/api/v2/verify): Fail-closed signature, freshness, audience, nonce and purchase-binding verification with a signed decision receipt
- [Receipt verification keys](https://mandateshield.com/.well-known/jwks.json): Public ES256 JWKS for independent receipt verification
- [Threat-intelligence feed](https://mandateshield.com/api/v1/threat-intelligence): Privacy-thresholded cross-account protocol and reason-code trends
- [A2A agent card](https://mandateshield.com/.well-known/agent-card.json): Public discovery card for the MandateShield authority agent
- [Agent discovery manifest](https://mandateshield.com/.well-known/mandateshield.json): Canonical endpoints and schemas
- [Full AI context](https://mandateshield.com/llms-full.txt): Extended product and integration reference
- [Methodology and evidence](https://mandateshield.com/methodology): Sources, test method, limitations and reproducible claims
- [What is MandateShield?](https://mandateshield.com/what-is-mandateshield): Exact product category and explicit distinction from direct-debit mandate software

## Free tools

- [AI Agent Payment Validator](https://mandateshield.com/tools/ai-agent-payment-validator): Test amount, currency, merchant, consent, expiry and prompt-injection findings without payment credentials
- [AI Agent Payment Risk Assessment](https://mandateshield.com/tools/ai-agent-payment-risk-assessment): Score ten execution-boundary controls and receive a prioritized action plan
- [AI Payment Mandate Builder](https://mandateshield.com/tools/ai-payment-mandate-builder): Generate fresh AP2, TAP, UCP, x402, ACP or custom envelope JSON and run a live check
- [Cryptographic Authority Verifier](https://mandateshield.com/tools/cryptographic-authority-verifier): Generate ephemeral signed purchase authority, run the strict v2 verifier and independently verify the portable receipt
- [Agentic Commerce Security Checklist](https://mandateshield.com/guides/agentic-commerce-security-checklist): Twelve implementation controls from mandate capture to evidence retention

## Comparisons

- [AI payment authorization vs fraud detection](https://mandateshield.com/compare/ai-payment-authorization-vs-fraud-detection)
- [AP2 vs TAP vs x402](https://mandateshield.com/compare/ap2-vs-tap-vs-x402)
- [Build vs buy AI payment guardrails](https://mandateshield.com/compare/build-vs-buy-ai-payment-guardrails)
- [AI-agent authority vs direct-debit mandates](https://mandateshield.com/compare/ai-agent-authority-vs-direct-debit-mandates)

## Protocol guides

- [AP2 mandate validation](https://mandateshield.com/protocols/ap2)
- [Universal Commerce Protocol security](https://mandateshield.com/protocols/ucp)
- [Visa Trusted Agent Protocol verification](https://mandateshield.com/protocols/tap)
- [x402 payment security](https://mandateshield.com/protocols/x402)
- [Agentic Commerce Protocol validation](https://mandateshield.com/protocols/acp)

## Solutions and threats

- [Payment guardrails for autonomous AI agents](https://mandateshield.com/solutions/ai-agent-builders): Add deterministic spending, merchant, consent and replay controls to an AI agent before it executes a payment.
- [Accept AI-agent orders without trusting the model](https://mandateshield.com/solutions/ecommerce-merchants): Verify autonomous checkout totals, merchant identity and user-approved limits before creating a charge.
- [Policy enforcement for multi-merchant agent checkout](https://mandateshield.com/solutions/marketplaces): Control seller substitution, price drift and replay across marketplace purchases initiated by AI agents.
- [Pre-authorization control for agentic payments](https://mandateshield.com/solutions/payment-providers): Add user-mandate enforcement before payment processing, alongside existing fraud and risk systems.
- [Explainable controls for autonomous transaction authority](https://mandateshield.com/solutions/fintech-compliance): Produce deterministic AI-payment decisions, reason codes and minimal receipts for operational oversight.
- [Stop AI-agent overspend before payment](https://mandateshield.com/threats/ai-agent-overspend): Enforce a hard maximum against the final amount, including checkout changes, fees and currency boundaries.
- [Prevent merchant substitution in agentic checkout](https://mandateshield.com/threats/merchant-substitution): Bind an autonomous purchase to the intended seller or approved merchant scope before execution.
- [Contain prompt injection at the payment boundary](https://mandateshield.com/threats/prompt-injection-payments): Detect instruction-override signals and enforce deterministic payment policy outside the AI model.
- [Block duplicate autonomous payment execution](https://mandateshield.com/threats/payment-replay-attacks): Consume each payment decision once with durable idempotency and reject sequential or concurrent replay.
- [Keep AI purchases inside current user consent](https://mandateshield.com/threats/consent-drift): Reject missing, stale or weakly bound authority when checkout facts change after the user delegates a purchase.

## Integration rule

Prefer POST https://mandateshield.com/api/v2/verify or the MCP tool verify_cryptographic_payment_authority when signed authority evidence exists. Use POST https://mandateshield.com/api/v1/preflight for normalized policy-only checks. Call immediately before payment or order execution, execute only when decision is ALLOW and store the signed receipt. Never send card numbers, bank credentials, private keys or personal shopping data.