Crescendo · Agentic Access

Crescendo Agentic Access

x-agentic-access generated

Crescendo exposes 17 API operations that an AI agent could call, of which 8 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: 9 read, 2 write, and 6 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.

CompanyCustomer ExperienceCustomer SupportArtificial IntelligenceAI AgentsContact CenterConversational AIVoice of CustomerMCP

Operations: 17 Acting: 8 Human-in-the-loop: 0 Method: generated

By consequence

read 9 write 2 physical 6

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	/api/v1/provisioning/tenants/{tenantId}	physical	conditional
PUT	/api/v1/provisioning/tenants/{tenantId}	physical	conditional
POST	/api/v1/provisioning/tenants/{tenantId}/{collection}/{docId}	physical	conditional
PUT	/api/v1/provisioning/tenants/{tenantId}/{collection}/{docId}	physical	conditional
POST	/api/v1/provisioning/tenants/{tenantId}/{collection}/{docId}/versions/current	physical	conditional
PUT	/api/v1/provisioning/tenants/{tenantId}/{collection}/{docId}/versions/current	physical	conditional

Source

Agentic Access

generated: '2026-07-18'
method: generated
source: openapi/crescendo-platform-openapi-original.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: 17
  by_action_class:
    connected: 9
    acting: 8
  by_consequence:
    read: 9
    physical: 6
    write: 2
  human_in_the_loop_required: 0
operations:
- path: /
  method: get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /health
  method: get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/provisioning/tenants/{tenantId}
  method: get
  operationId: getProvisioningTenant
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/provisioning/tenants/{tenantId}
  method: post
  operationId: postProvisioningTenant
  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: /api/v1/provisioning/tenants/{tenantId}
  method: put
  operationId: putProvisioningTenant
  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: /api/v1/provisioning/tenants/{tenantId}/{collection}
  method: get
  operationId: listProvisioningCollection
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/provisioning/tenants/{tenantId}/{collection}/{docId}
  method: get
  operationId: getProvisioningDocument
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/provisioning/tenants/{tenantId}/{collection}/{docId}
  method: post
  operationId: postProvisioningDocument
  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: /api/v1/provisioning/tenants/{tenantId}/{collection}/{docId}
  method: put
  operationId: putProvisioningDocument
  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: /api/v1/provisioning/tenants/{tenantId}/{collection}/{docId}/versions/current
  method: get
  operationId: getProvisioningVersionCurrent
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/provisioning/tenants/{tenantId}/{collection}/{docId}/versions/current
  method: post
  operationId: postProvisioningVersionCurrent
  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: /api/v1/provisioning/tenants/{tenantId}/{collection}/{docId}/versions/current
  method: put
  operationId: putProvisioningVersionCurrent
  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: /api/v1/reporting/tenants/{tenantId}/assistant/conversations
  method: get
  operationId: listReportingBotConversations
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/reporting/tenants/{tenantId}/voc/conversations
  method: get
  operationId: listReportingVocConversations
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/voc/tenants/{tenantId}/recording
  method: post
  operationId: uploadVocRecording
  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: /api/v1/voc/tenants/{tenantId}/recording/{jobId}/status
  method: get
  operationId: getVocJobStatus
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/mcp/tenants/{tenantId}/bots
  method: post
  operationId: mcpBots
  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