Kernel Agentic Access
Kernel exposes 184 API operations that an AI agent could call, of which 105 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: 79 read, 88 write, 3 physical, and 14 safety-critical.
14 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 | /browsers/{id_or_name}/computer/batch | safety-critical | required |
| POST | /browsers/{id_or_name}/computer/click_mouse | safety-critical | required |
| POST | /browsers/{id_or_name}/computer/clipboard/read | safety-critical | required |
| POST | /browsers/{id_or_name}/computer/clipboard/write | safety-critical | required |
| POST | /browsers/{id_or_name}/computer/cursor | safety-critical | required |
| POST | /browsers/{id_or_name}/computer/drag_mouse | safety-critical | required |
| POST | /browsers/{id_or_name}/computer/move_mouse | safety-critical | required |
| POST | /browsers/{id_or_name}/computer/press_key | safety-critical | required |
| POST | /browsers/{id_or_name}/computer/screenshot | safety-critical | required |
| POST | /browsers/{id_or_name}/computer/scroll | safety-critical | required |
| POST | /browsers/{id_or_name}/computer/type | safety-critical | required |
| DELETE | /browsers/{id_or_name}/fs/watch/{watch_id} | safety-critical | required |
| POST | /browsers/{id_or_name}/process/{process_id}/kill | safety-critical | required |
| POST | /browsers/{id_or_name}/replays/{replay_id}/stop | safety-critical | required |
| POST | /deployments | physical | conditional |
| DELETE | /deployments/{id} | physical | conditional |
| POST | /mpp/browsers | physical | conditional |
Source
Agentic Access
generated: '2026-11-10'
method: generated
source: openapi/kernel-api-keys-api-openapi.yml, openapi/kernel-apps-api-openapi.yml, openapi/kernel-audit-logs-api-openapi.yml,
openapi/kernel-authentication-api-openapi.yml, openapi/kernel-browser-computer-controls-api-openapi.yml,
openapi/kernel-browser-filesystem-api-openapi.yml, openapi/kernel-browser-logs-api-openapi.yml,
openapi/kernel-browser-playwright-api-openapi.yml, openapi/kernel-browser-pools-api-openapi.yml,
openapi/kernel-browser-processes-api-openapi.yml, openapi/kernel-browser-repl-api-openapi.yml,
openapi/kernel-browser-replays-api-openapi.yml, openapi/kernel-browser-telemetry-api-openapi.yml,
openapi/kernel-browser-webmcp-api-openapi.yml, openapi/kernel-browsers-api-openapi.yml, openapi/kernel-config-registry-api-openapi.yml,
openapi/kernel-credential-providers-api-openapi.yml, openapi/kernel-credentials-api-openapi.yml,
openapi/kernel-deployments-api-openapi.yml, openapi/kernel-extensions-api-openapi.yml, openapi/kernel-invocations-api-openapi.yml,
openapi/kernel-managed-auth-api-openapi.yml, openapi/kernel-organization-api-openapi.yml,
openapi/kernel-profiles-api-openapi.yml, openapi/kernel-projects-api-openapi.yml, openapi/kernel-proxies-api-openapi.yml,
openapi/kernel-search-api-openapi.yml, openapi/kernel-vaults-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: 184
by_action_class:
connected: 79
acting: 105
by_consequence:
read: 79
write: 88
safety-critical: 14
physical: 3
human_in_the_loop_required: 14
operations:
- path: /org/api_keys
method: get
operationId: listApiKeys
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /org/api_keys
method: post
operationId: postApiKeys
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: /org/api_keys/{id}
method: delete
operationId: deleteApiKeysById
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: /org/api_keys/{id}
method: get
operationId: getApiKeysById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /org/api_keys/{id}
method: patch
operationId: patchApiKeysById
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: /org/api_keys/{id}/rotate
method: post
operationId: rotateApiKey
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: /audit-logs
method: get
operationId: getAuditLogs
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /audit-logs/export/chunk
method: get
operationId: getAuditLogsExportChunk
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /audit-logs/export/destinations
method: get
operationId: getAuditLogExportDestinations
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /audit-logs/export/destinations
method: post
operationId: postAuditLogExportDestinations
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: /audit-logs/export/destinations/{id}
method: delete
operationId: deleteAuditLogExportDestinationsById
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: /audit-logs/export/destinations/{id}
method: get
operationId: getAuditLogExportDestinationsById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /audit-logs/export/destinations/{id}
method: patch
operationId: patchAuditLogExportDestinationsById
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: /audit-logs/export/destinations/{id}/test
method: post
operationId: testAuditLogExportDestinationById
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: /auth/context
method: get
operationId: getAuthContext
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/computer/batch
method: post
operationId: batchComputerAction
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: /browsers/{id_or_name}/computer/click_mouse
method: post
operationId: clickMouse
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: /browsers/{id_or_name}/computer/clipboard/read
method: post
operationId: readClipboard
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: /browsers/{id_or_name}/computer/clipboard/write
method: post
operationId: writeClipboard
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: /browsers/{id_or_name}/computer/cursor
method: post
operationId: setCursor
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: /browsers/{id_or_name}/computer/drag_mouse
method: post
operationId: dragMouse
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: /browsers/{id_or_name}/computer/get_mouse_position
method: post
operationId: getMousePosition
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/computer/move_mouse
method: post
operationId: moveMouse
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: /browsers/{id_or_name}/computer/press_key
method: post
operationId: pressKey
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: /browsers/{id_or_name}/computer/screenshot
method: post
operationId: takeScreenshot
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: /browsers/{id_or_name}/computer/scroll
method: post
operationId: scroll
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: /browsers/{id_or_name}/computer/type
method: post
operationId: typeText
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: /browsers/{id_or_name}/fs/create_directory
method: put
operationId: createDirectory
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: /browsers/{id_or_name}/fs/delete_directory
method: put
operationId: deleteDirectory
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: /browsers/{id_or_name}/fs/delete_file
method: put
operationId: deleteFile
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: /browsers/{id_or_name}/fs/download_dir_zip
method: get
operationId: downloadDirZip
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/fs/file_info
method: get
operationId: fileInfo
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/fs/list_files
method: get
operationId: listFiles
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/fs/move
method: put
operationId: movePath
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: /browsers/{id_or_name}/fs/read_file
method: get
operationId: readFile
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/fs/set_file_permissions
method: put
operationId: setFilePermissions
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: /browsers/{id_or_name}/fs/upload
method: post
operationId: uploadFiles
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: /browsers/{id_or_name}/fs/upload_zip
method: post
operationId: uploadZip
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: /browsers/{id_or_name}/fs/watch
method: post
operationId: startFsWatch
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: /browsers/{id_or_name}/fs/watch/{watch_id}
method: delete
operationId: stopFsWatch
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: /browsers/{id_or_name}/fs/watch/{watch_id}/events
method: get
operationId: streamFsEvents
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/fs/write_file
method: put
operationId: writeFile
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: /browsers/{id_or_name}/logs/stream
method: get
operationId: logsStream
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/playwright/execute
method: post
operationId: executePlaywrightCode
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: /browsers/{id_or_name}/playwright/executors
method: get
operationId: listPlaywrightExecutors
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/playwright/executors/{name}
method: delete
operationId: deletePlaywrightExecutor
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: /browser_pools
method: get
operationId: getBrowserPools
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browser_pools
method: post
operationId: postBrowserPools
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: /browser_pools/{id_or_name}
method: delete
operationId: deleteBrowserPoolsByIdOrName
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: /browser_pools/{id_or_name}
method: get
operationId: getBrowserPoolsByIdOrName
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browser_pools/{id_or_name}
method: patch
operationId: updateBrowserPoolsByIdOrName
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: /browser_pools/{id_or_name}/acquire
method: post
operationId: acquireFromBrowserPoolByIdOrName
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: /browser_pools/{id_or_name}/flush
method: post
operationId: flushBrowserPoolByIdOrName
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: /browser_pools/{id_or_name}/release
method: post
operationId: releaseToBrowserPoolByIdOrName
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: /browsers/{id_or_name}/process/exec
method: post
operationId: processExec
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: /browsers/{id_or_name}/process/spawn
method: post
operationId: processSpawn
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: /browsers/{id_or_name}/process/{process_id}/kill
method: post
operationId: processKill
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: /browsers/{id_or_name}/process/{process_id}/resize
method: post
operationId: processResize
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: /browsers/{id_or_name}/process/{process_id}/status
method: get
operationId: processStatus
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/process/{process_id}/stdin
method: post
operationId: processStdin
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: /browsers/{id_or_name}/process/{process_id}/stdout/stream
method: get
operationId: processStdoutStream
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/repl
method: post
operationId: executeBrowserRepl
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: /browsers/{id_or_name}/replays
method: get
operationId: listBrowsersReplays
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/replays
method: post
operationId: startBrowserReplayRecording
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: /browsers/{id_or_name}/replays/{replay_id}
method: get
operationId: getBrowsersReplaysById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/replays/{replay_id}/stop
method: post
operationId: stopBrowserReplayRecording
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: /browsers/{id_or_name}/telemetry/events
method: get
operationId: readBrowserTelemetryEvents
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/telemetry/stream
method: get
operationId: streamBrowserTelemetry
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /telemetry/destinations
method: get
operationId: getTelemetryDestinations
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /telemetry/destinations
method: post
operationId: postTelemetryDestinations
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: /telemetry/destinations/{id_or_name}
method: delete
operationId: deleteTelemetryDestinationByIdOrName
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: /telemetry/destinations/{id_or_name}
method: get
operationId: getTelemetryDestinationByIdOrName
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /telemetry/destinations/{id_or_name}
method: patch
operationId: patchTelemetryDestinationByIdOrName
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: /browsers/{id_or_name}/webmcp/custom-tools
method: get
operationId: listCustomWebMCPTools
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}/webmcp/custom-tools
method: post
operationId: addCustomWebMCPTools
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: /browsers/{id_or_name}/webmcp/custom-tools/{id}
method: delete
operationId: removeCustomWebMCPTool
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: /browsers/{id_or_name}/webmcp/invoke
method: post
operationId: invokeWebMCPTool
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: /browsers/{id_or_name}/webmcp/tools
method: get
operationId: listWebMCPTools
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers
method: get
operationId: getBrowsers
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers
method: post
operationId: postBrowsers
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: /browsers/{id_or_name}
method: delete
operationId: deleteBrowsersByIdOrName
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: /browsers/{id_or_name}
method: get
operationId: getBrowsersByIdOrName
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /browsers/{id_or_name}
method: patch
operationId: patchBrowsersByIdOrName
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: /browsers/{id_or_name}/curl
method: post
operationId: browserCurl
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: /browsers/{id_or_name}/extensions
method: post
operationId: uploadExtensionsToBrowser
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: /mpp/browsers
method: post
operationId: postMppBrowsers
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: /config-registry
method: get
operationId: getConfigRegistry
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /config-registry/analyses
method: get
operationId: getConfigRegistryAnalyses
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /config-registry/analyses/{id}
method: get
operationId: getConfigRegistryAnalysesById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /config-registry/analyses/{id}/cancel
method: post
operationId: postConfigRegistryAnalysesByIdCancel
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: /config-registry/lookup
method: post
operationId: postConfigRegistryLookup
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: /config-registry/resolve
method: post
operationId: postConfigRegistryResolve
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: /org/credential_providers
method: get
operationId: getCredentialProviders
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /org/credential_providers
method: post
operationId: postCredentialProviders
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: /org/credential_providers/{id}
method: delete
operationId: deleteCredentialProvidersById
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: /org/credential_providers/{id}
method: get
operationId: getCredentialProvidersById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
# --- truncated at 32 KB (55 KB total) ---
# Full source: https://artifacts.apis.io/kernel/agentic-access/kernel-agentic-access.yml
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=kernel-agentic-access&limit=10"
curl "https://apis.io/api/v1/tags/kernel-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. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.