Nuvei Agentic Access
Nuvei exposes 23 API operations that an AI agent could call, of which 23 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.
By consequence: 7 write, 15 physical, and 1 safety-critical.
1 operation are classed safety-critical and should require human-in-the-loop approval at runtime.
Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.
By consequence
Highest-consequence actions
The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.
| Method | Path | Consequence | Human-in-loop |
|---|---|---|---|
| POST | /disableUPO.do | safety-critical | required |
| POST | /accountCapture.do | physical | conditional |
| POST | /addUPOAPM.do | physical | conditional |
| POST | /addUPOCreditCard.do | physical | conditional |
| POST | /deleteUPO.do | physical | conditional |
| POST | /editUPOAPM.do | physical | conditional |
| POST | /editUPOCreditCard.do | physical | conditional |
| POST | /enableUPO.do | physical | conditional |
| POST | /getMerchantPaymentMethods.do | physical | conditional |
| POST | /getPaymentStatus.do | physical | conditional |
| POST | /getUserUPOs.do | physical | conditional |
| POST | /openOrder.do | physical | conditional |
| POST | /payment.do | physical | conditional |
| POST | /payout.do | physical | conditional |
| POST | /refundTransaction.do | physical | conditional |
| POST | /updateOrder.do | physical | conditional |