Clousd Agentic Access
Clousd exposes 78 API operations that an AI agent could call, of which 45 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: 33 read, 37 write, 3 physical, and 5 safety-critical.
5 operations 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.
API Evangelist recommendations, not provider rules. These classifications are generated heuristically from each operation's method, path and name. They suggest how an agent's access could be scoped. They are not authorization, approval or human-in-the-loop requirements that the provider enforces.
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 | Recommended human-in-loop |
|---|---|---|---|
| POST | /devices/{name}/act | safety-critical | required |
| POST | /devices/{name}/reset | safety-critical | required |
| POST | /devices/{name}/stop | safety-critical | required |
| POST | /runs/{id}/cancel | safety-critical | required |
| POST | /trash/{name}/restore | safety-critical | required |
| POST | /devices | physical | conditional |
| POST | /media/send | physical | conditional |
| POST | /webhooks/{id}/test | physical | conditional |
Source
Agentic Access
generated: '2026-11-10'
method: generated
source: openapi/clousd-com-account-api-openapi.yml, openapi/clousd-com-adb-api-openapi.yml,
openapi/clousd-com-ai-agents-api-openapi.yml, openapi/clousd-com-apps-api-openapi.yml, openapi/clousd-com-devices-api-openapi.yml,
openapi/clousd-com-files-and-media-api-openapi.yml, openapi/clousd-com-network-api-openapi.yml,
openapi/clousd-com-screen-and-input-api-openapi.yml, openapi/clousd-com-tasks-api-openapi.yml,
openapi/clousd-com-webhooks-api-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: 78
by_action_class:
connected: 33
acting: 45
by_consequence:
read: 33
write: 37
safety-critical: 5
physical: 3
human_in_the_loop_required: 5
operations:
- path: /usage
method: get
operationId: getUsage
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /incidents
method: get
operationId: getIncidents
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /health
method: get
operationId: getHealth
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /jobs
method: get
operationId: getJobs
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /jobs/{id}
method: get
operationId: getJobsById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}/adb
method: get
operationId: getDevicesByNameAdb
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}/adb
method: post
operationId: postDevicesByNameAdb
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: /devices/{name}/adb
method: delete
operationId: deleteDevicesByNameAdb
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: /devices/{name}/observe
method: get
operationId: getDevicesByNameObserve
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}/act
method: post
operationId: postDevicesByNameAct
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: /devices/{name}/op
method: post
operationId: postDevicesByNameOp
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: /devices/{name}/apk
method: post
operationId: postDevicesByNameApk
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: /apps
method: get
operationId: getApps
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /apps
method: post
operationId: postApps
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: /apps/{id}
method: get
operationId: getAppsById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /apps/{id}
method: delete
operationId: deleteAppsById
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: /apps/{id}/install
method: post
operationId: postAppsByIdInstall
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: /devices
method: get
operationId: getDevices
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices
method: post
operationId: postDevices
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: /devices/{name}
method: get
operationId: getDevicesByName
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}
method: delete
operationId: deleteDevicesByName
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: /devices/{name}/start
method: post
operationId: postDevicesByNameStart
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: /devices/{name}/stop
method: post
operationId: postDevicesByNameStop
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: /devices/{name}/restart
method: post
operationId: postDevicesByNameRestart
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: /devices/{name}/ice
method: get
operationId: getDevicesByNameIce
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}/quality
method: get
operationId: getDevicesByNameQuality
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /android
method: get
operationId: getAndroid
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /trash
method: get
operationId: getTrash
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /trash/{name}/restore
method: post
operationId: postTrashByNameRestore
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: /devices/{name}/reset
method: post
operationId: postDevicesByNameReset
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: /devices/{name}/screenrecord
method: get
operationId: getDevicesByNameScreenrecord
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}/label
method: post
operationId: postDevicesByNameLabel
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: /balance
method: get
operationId: getBalance
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}/files
method: put
operationId: putDevicesByNameFiles
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: /devices/{name}/media
method: post
operationId: postDevicesByNameMedia
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: /media
method: get
operationId: getMedia
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /media
method: post
operationId: postMedia
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: /media/folders
method: post
operationId: postMediaFolders
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: /media/move
method: post
operationId: postMediaMove
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: /media/send
method: post
operationId: postMediaSend
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: /devices/{name}/network
method: get
operationId: getDevicesByNameNetwork
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}/network
method: post
operationId: postDevicesByNameNetwork
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: /network/options
method: get
operationId: getNetworkOptions
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}/screenshot
method: get
operationId: getDevicesByNameScreenshot
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}/action
method: post
operationId: postDevicesByNameAction
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: /devices/{name}/input
method: post
operationId: postDevicesByNameInput
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: /devices/{name}/logs
method: get
operationId: getDevicesByNameLogs
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}/stream
method: get
operationId: getDevicesByNameStream
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /devices/{name}/stream
method: post
operationId: postDevicesByNameStream
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: /devices/{name}/stream/probe
method: post
operationId: postDevicesByNameStreamProbe
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: /schedules
method: get
operationId: getSchedules
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /schedules
method: post
operationId: postSchedules
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: /schedules/{id}/toggle
method: post
operationId: postSchedulesByIdToggle
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: /schedules/{id}/delete
method: post
operationId: postSchedulesByIdDelete
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: /runs
method: post
operationId: postRuns
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: /runs
method: get
operationId: getRuns
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /runs/{id}
method: get
operationId: getRunsById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /runs/{id}
method: delete
operationId: deleteRunsById
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: /runs/{id}/events
method: get
operationId: getRunsByIdEvents
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /runs/{id}/trajectory
method: get
operationId: getRunsByIdTrajectory
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /runs/{id}/steps/{n}.jpg
method: get
operationId: getRunsByIdSteps{n}Jpg
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /runs/{id}/answer
method: post
operationId: postRunsByIdAnswer
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: /runs/{id}/message
method: post
operationId: postRunsByIdMessage
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: /runs/{id}/cancel
method: post
operationId: postRunsByIdCancel
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: /schedules/{id}/run
method: post
operationId: postSchedulesByIdRun
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: /credentials
method: get
operationId: getCredentials
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /credentials
method: post
operationId: postCredentials
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: /credentials/{id}/fields
method: post
operationId: postCredentialsByIdFields
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: /credentials/{id}/fields/{type}
method: delete
operationId: deleteCredentialsByIdFieldsByType
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: /credentials/{id}
method: delete
operationId: deleteCredentialsById
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: /webhooks
method: get
operationId: getWebhooks
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /webhooks
method: post
operationId: postWebhooks
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: /webhooks/{id}
method: get
operationId: getWebhooksById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /webhooks/{id}
method: delete
operationId: deleteWebhooksById
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: /webhooks/{id}/rotate
method: post
operationId: postWebhooksByIdRotate
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: /webhooks/{id}/toggle
method: post
operationId: postWebhooksByIdToggle
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: /webhooks/{id}/test
method: post
operationId: postWebhooksByIdTest
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: /webhooks/{id}/deliveries
method: get
operationId: getWebhooksByIdDeliveries
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
Work with this as data
Every access contract here is available over the APIs.io API and to AI agents over MCP. Agentic Access is not yet its own endpoint on the v1 API. Reach it through catalog search and the tag graph, or the MCP server.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for agentic access
3 MCP tools reach this
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
curl "https://apis.io/api/v1/search?q=clousd-com-agentic-access&limit=10"
curl "https://apis.io/api/v1/tags/clousd-com-agentic-access"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.