unbrowse-ai · Agentic Access

unbrowse-ai Agentic Access

x-agentic-access generated

unbrowse-ai exposes 176 API operations that an AI agent could call, of which 86 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: 90 read, 78 write, 2 physical, and 6 safety-critical.

6 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.

AI AgentsDeveloper Tools

Operations: 176 Acting: 86 Human-in-the-loop: 6 Method: generated

By consequence

read 90 write 78 physical 2 safety-critical 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/connectors/disconnect	safety-critical	required
POST	/api/v1/connectors/disconnect	safety-critical	required
POST	/api/v1/org/keys/revoke	safety-critical	required
POST	/api/v1/org/keys/revoke	safety-critical	required
POST	/api/v1/relay/revoke	safety-critical	required
POST	/api/v1/relay/revoke	safety-critical	required
POST	/api/v1/org/users	physical	conditional
POST	/api/v1/org/users	physical	conditional

Source

Agentic Access

generated: '2026-10-30'
method: generated
source: openapi/unbrowse-ai-openapi.json, openapi/unbrowse-ai-openapi2.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: 176
  by_action_class:
    connected: 90
    acting: 86
  by_consequence:
    read: 90
    write: 78
    safety-critical: 6
    physical: 2
  human_in_the_loop_required: 6
operations:
- path: /api/v1/memory/requests
  method: get
  operationId: browserRequestMemory
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/runs
  method: post
  operationId: startRun
  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
    scope:
    - unbrowse
- path: /api/v1/scrape
  method: post
  operationId: scrape
  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
    scope:
    - unbrowse
- path: /api/v1/runs/{runId}
  method: get
  operationId: getRun
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/runs/{runId}/events
  method: get
  operationId: getRunEvents
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/runs/{runId}/responses
  method: post
  operationId: answerRun
  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
    scope:
    - unbrowse
- path: /api/v1/runs/{runId}/cancel
  method: post
  operationId: cancelRun
  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
    scope:
    - unbrowse
- path: /api/v1/browse-local
  method: post
  operationId: startLocalBrowse
  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
    scope:
    - unbrowse
- path: /api/v1/browse-local/{sessionId}/op
  method: post
  operationId: localBrowseOp
  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
    scope:
    - unbrowse
- path: /api/v1/browse-local/{sessionId}/next
  method: get
  operationId: localBrowseNext
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/browse-local/{sessionId}/result
  method: post
  operationId: localBrowseResult
  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
    scope:
    - unbrowse
- path: /api/v1/browse-local/{sessionId}
  method: delete
  operationId: closeLocalBrowse
  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
    scope:
    - unbrowse
- path: /api/v1/egress/{egressId}
  method: get
  operationId: getEgress
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/egress/{egressId}
  method: post
  operationId: answerEgress
  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
    scope:
    - unbrowse
- path: /api/v1/egress/{egressId}
  method: delete
  operationId: closeEgress
  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
    scope:
    - unbrowse
- path: /api/v1/capabilities/search
  method: post
  operationId: searchCapabilities
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/capabilities/{capabilityId}
  method: get
  operationId: getCapability
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/sites
  method: get
  operationId: listSites
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/sites/{host}
  method: get
  operationId: getSite
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/sites/{host}/readiness
  method: get
  operationId: getSiteReadiness
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/sites/{host}/official
  method: get
  operationId: getSiteOfficialMcp
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/sites/{host}/mcp
  method: post
  operationId: siteMcp
  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
    scope:
    - unbrowse
- path: /api/v1/sites/{host}/skill.md
  method: get
  operationId: getSiteSkill
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/marketplace
  method: get
  operationId: listMarketplace
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/queries
  method: get
  operationId: listQueries
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/queries
  method: post
  operationId: compileQuery
  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
    scope:
    - unbrowse
- path: /api/v1/queries/{queryId}
  method: get
  operationId: getQuery
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/queries/{queryId}
  method: delete
  operationId: deleteQuery
  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
    scope:
    - unbrowse
- path: /api/v1/queries/{queryId}/settings
  method: post
  operationId: querySettings
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/queries/{queryId}/recompile
  method: post
  operationId: recompileQuery
  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
    scope:
    - unbrowse
- path: /api/v1/q/{queryId}
  method: get
  operationId: callQuery
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/q/{queryId}
  method: post
  operationId: callQueryPost
  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
    scope:
    - unbrowse
- path: /api/v1/connectors
  method: get
  operationId: listConnections
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/connectors/apps
  method: get
  operationId: searchConnectableApps
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/connectors/connect
  method: post
  operationId: connectApp
  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
    scope:
    - unbrowse
- path: /api/v1/connectors/disconnect
  method: post
  operationId: disconnectApp
  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
    scope:
    - unbrowse
- path: /api/v1/connectors/tools
  method: get
  operationId: listConnectedTools
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/connectors/call
  method: post
  operationId: callConnectedTool
  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
    scope:
    - unbrowse
- path: /api/v1/logins
  method: get
  operationId: listLogins
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/logins
  method: post
  operationId: saveLogin
  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
    scope:
    - unbrowse
- path: /api/v1/logins/remove
  method: post
  operationId: removeLogin
  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
    scope:
    - unbrowse
- path: /api/v1/vault
  method: get
  operationId: getVault
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/accounts/connections
  method: post
  operationId: connectAccount
  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
    scope:
    - unbrowse
- path: /api/v1/accounts/register
  method: post
  operationId: registerAccount
  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
    scope:
    - unbrowse
- path: /api/v1/learn
  method: post
  operationId: learn
  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
    scope:
    - unbrowse
- path: /api/v1/learned/{id}
  method: get
  operationId: getLearned
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/learned/{id}/harness.yaml
  method: get
  operationId: getLearnedHarness
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/learned/{id}/skill.md
  method: get
  operationId: getLearnedSkill
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/skills
  method: get
  operationId: listSkills
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/org
  method: get
  operationId: getOrg
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/org
  method: post
  operationId: createOrg
  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
    scope:
    - unbrowse
- path: /api/v1/org/keys
  method: post
  operationId: mintOrgKey
  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
    scope:
    - unbrowse
- path: /api/v1/org/keys/revoke
  method: post
  operationId: revokeOrgKey
  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
    scope:
    - unbrowse
- path: /api/v1/org/users
  method: post
  operationId: mintEndUserKey
  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
    scope:
    - unbrowse
- path: /api/v1/org/settings
  method: post
  operationId: setOrgSettings
  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
    scope:
    - unbrowse
- path: /api/v1/connect/{requestId}
  method: get
  operationId: getConnectLink
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/connect/{requestId}
  method: post
  operationId: fulfilConnectLink
  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
    scope:
    - unbrowse
- path: /api/v1/replays
  method: get
  operationId: listReplays
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/replays/{sid}
  method: get
  operationId: getReplay
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/replays/{sid}
  method: delete
  operationId: deleteReplay
  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
    scope:
    - unbrowse
- path: /api/v1/replays/{sid}/timeline
  method: get
  operationId: getReplayTimeline
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/replays/search
  method: post
  operationId: searchReplays
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/replays/ask
  method: post
  operationId: askReplays
  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
    scope:
    - unbrowse
- path: /api/v1/sites/{host}/openapi.json
  method: get
  operationId: getSiteOpenApi
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/sites/{host}/call/{tool}
  method: post
  operationId: callSiteTool
  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
    scope:
    - unbrowse
- path: /api/v1/index
  method: post
  operationId: startIndexJob
  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
    scope:
    - unbrowse
- path: /api/v1/index
  method: get
  operationId: listIndexJobs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/index/{jobId}
  method: get
  operationId: getIndexJob
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/learned
  method: get
  operationId: listLearned
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/cookies
  method: post
  operationId: importCookies
  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
    scope:
    - unbrowse
- path: /api/v1/cookies/{site}
  method: delete
  operationId: forgetSiteSession
  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
    scope:
    - unbrowse
- path: /api/v1/relay/status
  method: get
  operationId: browserRelayStatus
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/relay/revoke
  method: post
  operationId: revokeBrowserRelay
  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
    scope:
    - unbrowse
- path: /api/v1/apps
  method: get
  operationId: listApps
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/scopes
  method: get
  operationId: listScopes
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/scopes
  method: post
  operationId: saveScope
  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
    scope:
    - unbrowse
- path: /api/v1/scopes/{slug}
  method: get
  operationId: getScope
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/scopes/{slug}
  method: put
  operationId: updateScope
  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
    scope:
    - unbrowse
- path: /api/v1/scopes/{slug}
  method: delete
  operationId: deleteScope
  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
    scope:
    - unbrowse
- path: /api/v1/tools/triage
  method: get
  operationId: toolTriage
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/tools/triage/jev
  method: post
  operationId: toolTriageJev
  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
    scope:
    - unbrowse
- path: /api/v1/tools/{capabilityId}/{action}
  method: post
  operationId: changeTool
  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
    scope:
    - unbrowse
- path: /api/v1/workspace/sharing
  method: get
  operationId: getSharing
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/workspace/sharing
  method: put
  operationId: setSharing
  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
    scope:
    - unbrowse
- path: /api/v1/workspace/session-reuse
  method: get
  operationId: getSessionReuse
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/workspace/session-reuse
  method: put
  operationId: setSessionReuse
  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
    scope:
    - unbrowse
- path: /api/v1/usage
  method: get
  operationId: getUsage
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/me
  method: get
  operationId: getMe
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/memory/requests
  method: get
  operationId: browserRequestMemory
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/runs
  method: post
  operationId: startRun
  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
    scope:
    - unbrowse
- path: /api/v1/scrape
  method: post
  operationId: scrape
  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
    scope:
    - unbrowse
- path: /api/v1/runs/{runId}
  method: get
  operationId: getRun
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/runs/{runId}/events
  method: get
  operationId: getRunEvents
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/runs/{runId}/responses
  method: post
  operationId: answerRun
  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
    scope:
    - unbrowse
- path: /api/v1/runs/{runId}/cancel
  method: post
  operationId: cancelRun
  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
    scope:
    - unbrowse
- path: /api/v1/browse-local
  method: post
  operationId: startLocalBrowse
  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
    scope:
    - unbrowse
- path: /api/v1/browse-local/{sessionId}/op
  method: post
  operationId: localBrowseOp
  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
    scope:
    - unbrowse
- path: /api/v1/browse-local/{sessionId}/next
  method: get
  operationId: localBrowseNext
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/browse-local/{sessionId}/result
  method: post
  operationId: localBrowseResult
  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
    scope:
    - unbrowse
- path: /api/v1/browse-local/{sessionId}
  method: delete
  operationId: closeLocalBrowse
  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
    scope:
    - unbrowse
- path: /api/v1/egress/{egressId}
  method: get
  operationId: getEgress
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/egress/{egressId}
  method: post
  operationId: answerEgress
  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
    scope:
    - unbrowse
- path: /api/v1/egress/{egressId}
  method: delete
  operationId: closeEgress
  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
    scope:
    - unbrowse
- path: /api/v1/capabilities/search
  method: post
  operationId: searchCapabilities
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse
- path: /api/v1/capabilities/{capabilityId}
  method: get
  operationId: getCapability
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - unbrowse


# --- truncated at 32 KB (52 KB total) ---
# Full source: https://artifacts.apis.io/unbrowse-ai/agentic-access/unbrowse-ai-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.

All 92 tools →

Call it yourself

curl for this page

Search the catalog

curl "https://apis.io/api/v1/search?q=unbrowse-ai-agentic-access&limit=10"

Everything under a tag

curl "https://apis.io/api/v1/tags/unbrowse-ai-agentic-access"

Discovery needs no key. Ratings and market analysis are Pro.

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.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.