Uber Eats · Agentic Access

Uber Eats Agentic Access

x-agentic-access generated

Uber Eats exposes 17 API operations that an AI agent could call, of which 10 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: 7 read, 8 write, and 2 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.

Uber EatsUber DirectFood DeliveryLast-Mile LogisticsRestaurantsMenusOrdersFulfillmentCourierOAuth2
Operations: 17 Acting: 10 Human-in-the-loop: 0 Method: generated

By consequence

read 7 write 8 physical 2

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.

MethodPathConsequenceHuman-in-loop
POST /eats/orders/{order_id}/accept_pos_order physical conditional
POST /eats/orders/{order_id}/cancel physical conditional

Source

Agentic Access

Raw ↑ 
generated: '2026-07-15'
method: generated
source: openapi/uber-direct-openapi.yml, openapi/uber-eats-openapi.yml
description: Recommended x-agentic-access execution contracts, classified heuristically from
  the OpenAPI. A governance starting point for exposing this API to AI agents — review and bind
  audience per deployment. See research/curity/agentic-governance/.
summary:
  operations: 17
  by_action_class:
    acting: 10
    connected: 7
  by_consequence:
    write: 8
    read: 7
    physical: 2
  human_in_the_loop_required: 0
operations:
- path: /customers/{customer_id}/delivery_quotes
  method: post
  operationId: createQuote
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /customers/{customer_id}/deliveries
  method: post
  operationId: createDelivery
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /customers/{customer_id}/deliveries
  method: get
  operationId: listDeliveries
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /customers/{customer_id}/deliveries/{delivery_id}
  method: get
  operationId: getDelivery
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /customers/{customer_id}/deliveries/{delivery_id}
  method: post
  operationId: updateDelivery
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /customers/{customer_id}/deliveries/{delivery_id}/cancel
  method: post
  operationId: cancelDelivery
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /customers/{customer_id}/deliveries/{delivery_id}/proof-of-delivery
  method: post
  operationId: getProofOfDelivery
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /eats/stores
  method: get
  operationId: getStores
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /eats/stores/{store_id}
  method: get
  operationId: getStore
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /eats/store/{store_id}/status
  method: post
  operationId: setStoreStatus
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /eats/stores/{store_id}/menus
  method: get
  operationId: getMenu
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /eats/stores/{store_id}/menus
  method: put
  operationId: upsertMenu
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /eats/stores/{store_id}/menus/items/{item_id}
  method: post
  operationId: updateMenuItem
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /eats/stores/{store_id}/created-orders
  method: get
  operationId: getCreatedOrders
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /eats/order/{order_id}
  method: get
  operationId: getOrder
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /eats/orders/{order_id}/accept_pos_order
  method: post
  operationId: acceptPosOrder
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /eats/orders/{order_id}/cancel
  method: post
  operationId: cancelOrder
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required