SumUp Agentic Access
SumUp exposes 39 API operations that an AI agent could call, of which 19 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: 20 read, 11 write, 7 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 | /v0.1/merchants/{merchant_code}/readers/{reader_id}/terminate | safety-critical | required |
| POST | /v0.1/checkouts | physical | conditional |
| PUT | /v0.1/checkouts/{checkout_id} | physical | conditional |
| DELETE | /v0.1/checkouts/{checkout_id} | physical | conditional |
| DELETE | /v0.1/customers/{customer_id}/payment-instruments/{token} | physical | conditional |
| POST | /v0.1/merchants/{merchant_code}/readers/{reader_id}/checkout | physical | conditional |
| PUT | /v0.2/checkouts/{checkout_id}/apple-pay-session | physical | conditional |
| POST | /v1.0/merchants/{merchant_code}/payments/{transaction_id}/refunds | physical | conditional |