Loop Agentic Access
Loop exposes 41 API operations that an AI agent could call, of which 15 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: 26 read, 6 write, and 9 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 |
|---|---|---|---|
| POST | /v1/artifacts/payable-invoice-record | physical | conditional |
| POST | /v1/artifacts/purchase-order-record | physical | conditional |
| POST | /v1/artifacts/receivable-invoice-record | physical | conditional |
| POST | /v1/artifacts/shipment-record | physical | conditional |
| POST | /v1/factoring-relationships | physical | conditional |
| POST | /v1/invoicing-relationships | physical | conditional |
| POST | /v1/organizations/create-organization-with-payment-detail | physical | conditional |
| DELETE | /v1/receivable-invoices/{qid} | physical | conditional |
| PUT | /v1/receivable-invoices/{qid}/void | physical | conditional |