Marriott International Agentic Access

x-agentic-access generated

Marriott International exposes 13 API operations that an AI agent could call, of which 11 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: 2 read, 8 write, 2 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.

TravelUnited StatesHospitalityHotelsBookingDistributionLoyaltyShort Term RentalCorporate Travel

Operations: 13 Acting: 11 Human-in-the-loop: 1 Method: generated

By consequence

read 2 write 8 physical 2 safety-critical 1

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	/actuator/loggers/ROOT	safety-critical	required
POST	/loyalty/v1/account-merge	physical	conditional
POST	/partners/v1/internet-portal/purchase-update	physical	conditional

Source

Agentic Access

generated: '2026-07-28'
method: generated
source: openapi/marriott-commerce-payment-processor-api-openapi.json, openapi/marriott-data-collection-api-openapi.json,
  openapi/marriott-finance-status-notifier-api-openapi.json, openapi/marriott-hotel-operations-ara-api-openapi.json,
  openapi/marriott-loyalty-account-merge-api-openapi.json, openapi/marriott-tip-internet-portal-api-openapi.json
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: 13
  by_action_class:
    acting: 11
    connected: 2
  by_consequence:
    write: 8
    read: 2
    safety-critical: 1
    physical: 2
  human_in_the_loop_required: 1
operations:
- path: /freeway/service
  method: post
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    scope:
    - MANAGE_ACCT_AUTH_E
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /osd/v1/stays/{confirmation-number}/data-collection
  method: post
  operationId: DataCollectionEvent
  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: /status
  method: put
  operationId: updateProcessingStatus
  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
    scope:
    - write
- path: /retrieveConfigsMonitoredByConfigWatcher
  method: get
  operationId: retrieveConfigsMonitoredByConfigWatcher
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - write
- path: /actuator/loggers/ROOT
  method: post
  operationId: changeLogger
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
    scope:
    - write
- path: /data
  method: post
  operationId: createAdapterProcessingStatusPefTestData
  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
    scope:
    - write
- path: /data
  method: delete
  operationId: deletePerfTestData
  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
    scope:
    - write
- path: /v1/hotelops/ara/preview-submit
  method: post
  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: /loyalty/v1/account-merge
  method: post
  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: /v3/ent-auth/sso/token
  method: post
  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: /partners/v1/internet-portal/landing-page
  method: get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /partners/v1/internet-portal/guest-validation
  method: post
  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: /partners/v1/internet-portal/purchase-update
  method: post
  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