Capy Agentic Access
Capy exposes 37 API operations that an AI agent could call, of which 19 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: 18 read, 17 write, 1 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.
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 |
|---|---|---|---|
| POST | /v1/threads/{threadId}/stop | safety-critical | required |
| POST | /v1/threads/{threadId}/message | physical | conditional |
Source
Agentic Access
generated: '2026-07-18'
method: generated
source: openapi/capy-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: 37
by_action_class:
connected: 18
acting: 19
by_consequence:
read: 18
write: 17
safety-critical: 1
physical: 1
human_in_the_loop_required: 1
operations:
- path: /v1/threads
method: get
operationId: listThreads
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/threads
method: post
operationId: createAndStartThread
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: /v1/threads/{threadId}
method: get
operationId: getThread
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/threads/{threadId}/stop
method: post
operationId: stopThread
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: /v1/threads/{threadId}/archive
method: post
operationId: archiveThread
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: /v1/threads/{threadId}/unarchive
method: post
operationId: unarchiveThread
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: /v1/threads/{threadId}/session-token
method: get
operationId: getThreadSessionToken
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/threads/{threadId}/message
method: post
operationId: sendThreadMessage
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: /v1/threads/{threadId}/messages
method: get
operationId: listThreadMessages
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/threads/{threadId}/tags
method: put
operationId: setThreadTags
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: /v1/tasks/{taskId}
method: get
operationId: getTask
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/tasks/{taskId}/diff
method: get
operationId: getTaskDiff
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects
method: get
operationId: listProjects
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects/{projectId}
method: get
operationId: getProject
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects/{projectId}/tags
method: get
operationId: listThreadTags
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects/{projectId}/tags
method: post
operationId: createThreadTag
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: /v1/models
method: get
operationId: listModels
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/usage
method: get
operationId: getUsage
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects/{projectId}/setup
method: get
operationId: getSetup
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects/{projectId}/setup
method: patch
operationId: updateSetup
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: /v1/projects/{projectId}/snapshots
method: get
operationId: getSnapshots
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects/{projectId}/snapshots
method: patch
operationId: updateSnapshots
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: /v1/projects/{projectId}/browser-snapshots
method: get
operationId: listBrowserSnapshots
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects/{projectId}/browser-snapshots
method: post
operationId: createBrowserSnapshot
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: /v1/projects/{projectId}/browser-snapshots/{snapshotId}
method: get
operationId: getBrowserSnapshot
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects/{projectId}/browser-snapshots/{snapshotId}
method: patch
operationId: updateBrowserSnapshot
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: /v1/projects/{projectId}/browser-snapshots/{snapshotId}
method: delete
operationId: deleteBrowserSnapshot
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: /v1/projects/{projectId}/environment-variables/personal
method: get
operationId: listPersonalEnvironmentVariables
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects/{projectId}/environment-variables/personal
method: put
operationId: upsertPersonalEnvironmentVariables
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: /v1/projects/{projectId}/environment-variables/personal/{name}
method: delete
operationId: deletePersonalEnvironmentVariable
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: /v1/projects/{projectId}/automations
method: get
operationId: listAutomations
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects/{projectId}/automations
method: post
operationId: createAutomation
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: /v1/projects/{projectId}/automations/{automationId}
method: get
operationId: getAutomation
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /v1/projects/{projectId}/automations/{automationId}
method: patch
operationId: updateAutomation
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: /v1/projects/{projectId}/automations/{automationId}
method: delete
operationId: deleteAutomation
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: /v1/projects/{projectId}/automations/{automationId}/trigger
method: post
operationId: triggerAutomation
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: /v1/sessions/verify
method: post
operationId: verifySession
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