dLocal Agentic Access
dLocal exposes 49 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: 22 read, 13 write, 13 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 |
|---|---|---|---|
| DELETE | /v2/accounts/{account_id}/bank-accounts/{bank_account_id} | safety-critical | required |
| POST | /chargebacks/simulate | physical | conditional |
| POST | /payments | physical | conditional |
| POST | /payments/{authorization_id}/cancel | physical | conditional |
| POST | /payments/{authorization_id}/captures | physical | conditional |
| POST | /payments/{payment_id}/cancel | physical | conditional |
| POST | /payouts/v3 | physical | conditional |
| POST | /payouts/v3/quotes | physical | conditional |
| POST | /payouts/v3/{payout_id}/cancel | physical | conditional |
| POST | /payouts/v3/{payout_id}/release | physical | conditional |
| POST | /refunds | physical | conditional |
| POST | /secure_payments | physical | conditional |
| POST | /v2/transfers | physical | conditional |
| POST | /v2/transfers/{transfer_id}/cancel | physical | conditional |