Fiserv Agentic Access
Fiserv exposes 42 API operations that an AI agent could call, of which 27 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: 15 read, 15 write, and 12 physical.
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 |
|---|---|---|---|
| PUT | /auth | physical | conditional |
| POST | /banking/payments | physical | conditional |
| POST | /banking/payments/{paymentId}/reverse | physical | conditional |
| POST | /banking/transfers | physical | conditional |
| POST | /payments-vas/v1/3ds/authentication | physical | conditional |
| POST | /payments-vas/v1/accounts/verification | physical | conditional |
| POST | /payments-vas/v1/tokens | physical | conditional |
| POST | /payments/v1/charges | physical | conditional |
| POST | /payments/v1/charges/{transactionId}/cancel | physical | conditional |
| POST | /payments/v1/charges/{transactionId}/capture | physical | conditional |
| POST | /payments/v1/charges/{transactionId}/refund | physical | conditional |
| PUT | /refund | physical | conditional |