grubhub Agentic Access
grubhub exposes 35 API operations that an AI agent could call, of which 18 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: 17 read, 12 write, 3 physical, and 3 safety-critical.
3 operations 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 |
|---|---|---|---|
| PUT | /pos/v1/merchant/{merchant_id}/menu/schedules/overrides/external | safety-critical | required |
| POST | /pos/v1/merchant/{merchant_id}/schedules/overrides | safety-critical | required |
| DELETE | /pos/v1/merchant/{merchant_id}/schedules/overrides | safety-critical | required |
| POST | /pos/v1/merchant/{merchant_long_id}/orders/{order_uuid}/confirm | physical | conditional |
| POST | /pos/v1/merchant/{merchant_long_id}/orders/{order_uuid}/delivery/proxy-phone | physical | conditional |
| PUT | /pos/v1/merchant/{merchant_long_id}/orders/{order_uuid}/status | physical | conditional |