Barndoor · Agentic Access

Barndoor Agentic Access

x-agentic-access generated

Barndoor exposes 26 API operations that an AI agent could call, of which 13 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: 13 read, 12 write, 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.

AI AgentsAI GovernanceAgentic AIMCPModel Context ProtocolPolicy EnforcementOAuthIdentitySecurityAuditControl Plane
Operations: 26 Acting: 13 Human-in-the-loop: 1 Method: generated

By consequence

read 13 write 12 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.

MethodPathConsequenceHuman-in-loop
PUT /api/policies/restrictions/disable/{restriction_name} safety-critical required

Source

Agentic Access

Raw ↑ 
generated: '2026-07-15'
method: generated
source: openapi/barndoor-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: 26
  by_action_class:
    connected: 13
    acting: 13
  by_consequence:
    read: 13
    write: 12
    safety-critical: 1
  human_in_the_loop_required: 1
operations:
- path: /api/agents/counts
  method: get
  operationId: getAgentCounts
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/agents/{agent_id}
  method: delete
  operationId: unregisterAgent
  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/agents/{agent_id}
  method: get
  operationId: getAgent
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/agents
  method: get
  operationId: listAgents
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/agents
  method: post
  operationId: registerAgent
  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/servers/{server_id}/connection
  method: delete
  operationId: deleteConnection
  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/servers/{server_id}/connection
  method: get
  operationId: getConnectionStatus
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/servers/{server_id}/connect
  method: post
  operationId: initiateConnection
  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: /mcp/{mcp_server_name}
  method: get
  operationId: proxyMcpRequest
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v2/policies/{policy_id}/clone
  method: post
  operationId: clone_policy_admin_v2_policies__policy_id__clone_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: /api/policy
  method: post
  operationId: publish_cerbos_policy_admin_policy_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: /api/policies/restrictions/disable/{restriction_name}
  method: put
  operationId: disable_restriction_admin_policies_restrictions_disable__restriction_name__put
  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
- path: /api/policies/restrictions/enable/{restriction_name}
  method: put
  operationId: enable_restriction_admin_policies_restrictions_enable__restriction_name__put
  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/v2/policies/filter-definitions
  method: get
  operationId: get_filter_definitions_admin_v2_policies_filter_definitions_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v2/policies/summary
  method: get
  operationId: get_policies_summary_admin_v2_policies_summary_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v2/policies/{policy_id}
  method: get
  operationId: get_policy_admin_v2_policies__policy_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v2/policies/{policy_id}
  method: patch
  operationId: update_policy_admin_v2_policies__policy_id__patch
  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/v2/policies
  method: get
  operationId: list_policies_admin_v2_policies_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v2/policies/{policy_id}/revisions
  method: get
  operationId: list_policy_revisions_admin_v2_policies__policy_id__revisions_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v2/policies/validate
  method: post
  operationId: validate_policy_admin_v2_policies_validate_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: /api/servers
  method: post
  operationId: createServer
  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/servers
  method: get
  operationId: listServers
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/servers/{server_id}
  method: delete
  operationId: deleteServer
  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/servers/{server_id}
  method: get
  operationId: getServer
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/servers/{server_id}
  method: put
  operationId: updateServer
  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: /sse/{mcp_server_name}
  method: get
  operationId: proxySSERequest
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none