Trajectory Agentic Access
Trajectory exposes 237 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: 151 read, 74 write, 10 physical, and 2 safety-critical.
2 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 |
|---|---|---|---|
| DELETE | /api/v1/organizations/{organization_id}/api-keys/{key_hash} | safety-critical | required |
| DELETE | /api/v1/secrets/{secret_id} | safety-critical | required |
| POST | /api/v1/billing/payment-method/portal | physical | conditional |
| POST | /api/v1/billing/purchases | physical | conditional |
| POST | /api/v1/deploy | physical | conditional |
| DELETE | /api/v1/deploy/{deployment_id} | physical | conditional |
| POST | /api/v1/deploy/{deployment_id}/cancel | physical | conditional |
| POST | /api/v1/deploy/{deployment_id}/chat/completions | physical | conditional |
| POST | /api/v1/deploy/{deployment_id}/chat/completions | physical | conditional |
| POST | /api/v1/deploy/{deployment_id}/promote | physical | conditional |
| POST | /api/v1/deploy/{deployment_id}/retry | physical | conditional |
| POST | /api/v1/deploy/{deployment_id}/unpromote | physical | conditional |
Source
Agentic Access
generated: '2026-11-10'
method: generated
source: openapi/trajectory-agents-api-openapi.yml, openapi/trajectory-aperture-api-openapi.yml,
openapi/trajectory-api-keys-api-openapi.yml, openapi/trajectory-artifacts-api-openapi.yml,
openapi/trajectory-auth-api-openapi.yml, openapi/trajectory-benchmark-ingestion-api-openapi.yml,
openapi/trajectory-benchmarks-api-openapi.yml, openapi/trajectory-billing-api-openapi.yml,
openapi/trajectory-deployments-api-openapi.yml, openapi/trajectory-diagnostics-api-openapi.yml,
openapi/trajectory-eval-api-openapi.yml, openapi/trajectory-experiments-api-openapi.yml, openapi/trajectory-inference-api-openapi.yml,
openapi/trajectory-krun-api-openapi.yml, openapi/trajectory-model-endpoints-api-openapi.yml,
openapi/trajectory-model-slugs-api-openapi.yml, openapi/trajectory-organizations-api-openapi.yml,
openapi/trajectory-pipelines-api-openapi.yml, openapi/trajectory-regression-reports-api-openapi.yml,
openapi/trajectory-sandboxes-api-openapi.yml, openapi/trajectory-secrets-api-openapi.yml,
openapi/trajectory-sherlock-api-openapi.yml, openapi/trajectory-supported-models-api-openapi.yml,
openapi/trajectory-tcli-api-openapi.yml, openapi/trajectory-telemetry-api-openapi.yml, openapi/trajectory-training-api-openapi.yml,
openapi/trajectory-trajectories-api-openapi.yml, openapi/trajectory-wandb-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: 237
by_action_class:
acting: 86
connected: 151
by_consequence:
write: 74
read: 151
safety-critical: 2
physical: 10
human_in_the_loop_required: 2
operations:
- path: /api/v1/agents
method: post
operationId: createAgent
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/agents
method: get
operationId: listAgents
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}
method: get
operationId: getAgentById
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}
method: patch
operationId: updateAgent
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/agents/{agent_id}
method: delete
operationId: deleteAgent
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/agents/name/{name}
method: get
operationId: getAgentByName
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/benchmarks
method: get
operationId: listAgentBenchmarks
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/benchmarks
method: delete
operationId: deleteBenchmarkByName
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/agents/{agent_id}/benchmarks/latest
method: get
operationId: getBenchmarkByName
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/benchmarks/versions
method: get
operationId: listBenchmarkVersionsByName
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/training-runs
method: post
operationId: attachAgentTrainingRun
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/agents/{agent_id}/training-runs
method: get
operationId: listAgentTrainingRuns
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/evaluation-runs
method: get
operationId: listAgentEvaluationRuns
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/deployments
method: get
operationId: listAgentDeployments
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/overview
method: get
operationId: getAgentOverview
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/evaluation-runs/{eval_run_id}
method: get
operationId: getAgentEvaluationRun
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/training-runs/{training_run_id}/evaluation-series
method: get
operationId: getAgentTrainingEvaluationSeries
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/workspace
method: get
operationId: getAgentWorkspace
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/traces
method: get
operationId: listAgentProductionTraces
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/traces/{trajectory_id}
method: get
operationId: getAgentProductionTrace
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/agents/{agent_id}/traces/{trajectory_id}
method: patch
operationId: updateAgentProductionTraceFeedback
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/train/{training_run_id}/trajectory-view
method: get
operationId: getTrainingRunTrajectoryView
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/train/{training_run_id}/trajectory-view/reward-history
method: get
operationId: getTrainingRunTrajectoryRewardHistory
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/train/{training_run_id}/trajectory-view/global-steps/{global_step}/summary
method: get
operationId: getTrainingRunTrajectorySummary
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/train/{training_run_id}/trajectory-view/global-steps/{global_step}/trajectories
method: get
operationId: listTrainingRunTrajectoryViewItems
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/train/{training_run_id}/trajectory-view/trajectories/{trajectory_id}/steps/{step_index}/tokens
method: get
operationId: getTrainingRunTrajectoryStepTokens
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/eval/{eval_run_id}/trajectory-view
method: get
operationId: getEvalRunTrajectoryView
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/eval/{eval_run_id}/trajectory-view/reward-history
method: get
operationId: getEvalRunTrajectoryRewardHistory
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/eval/{eval_run_id}/trajectory-view/global-steps/{global_step}/summary
method: get
operationId: getEvalRunTrajectorySummary
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/eval/{eval_run_id}/trajectory-view/global-steps/{global_step}/trajectories
method: get
operationId: listEvalRunTrajectoryViewItems
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/eval/{eval_run_id}/trajectory-view/trajectories/{trajectory_id}/steps/{step_index}/tokens
method: get
operationId: getEvalRunTrajectoryStepTokens
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}
method: get
operationId: getApertureXid
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/trajectories
method: get
operationId: listApertureXidTrajectories
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/global-steps/{global_step}/summary
method: get
operationId: getApertureXidStepSummary
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/global-steps/{global_step}/trajectories
method: get
operationId: listApertureXidUidTrajectories
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/global-steps/{global_step}/search
method: get
operationId: searchApertureXidStepMessages
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/trajectories/{trajectory_id}/task-trajectories
method: get
operationId: listApertureXidTaskTrajectories
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/trajectory/steps
method: get
operationId: listApertureXidTrajectorySteps
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/trajectory/task
method: get
operationId: getApertureXidTrajectoryTask
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/trajectories/{trajectory_id}/messages/{message_id}
method: get
operationId: getApertureTrajectoryMessage
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/checkpoint-rewards
method: get
operationId: listApertureXidCheckpointRewards
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/trajectories/{trajectory_id}
method: get
operationId: inspectApertureTrajectory
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/trajectory/grading
method: get
operationId: getApertureXidTrajectoryGrading
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/trajectory/workspace
method: get
operationId: getApertureXidTrajectoryWorkspace
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/trajectory/workspace/file
method: get
operationId: downloadApertureXidTrajectoryWorkspaceFile
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/trajectory/download
method: get
operationId: downloadApertureXidTrajectory
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/dataset-trajectories/workspace
method: get
operationId: getApertureDatasetTrajectoryWorkspace
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/dataset-trajectories/workspace/file
method: get
operationId: downloadApertureDatasetTrajectoryWorkspaceFile
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/dataset-trajectories/download
method: get
operationId: downloadApertureDatasetTrajectory
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/datasets
method: get
operationId: listApertureDatasets
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/dataset-trajectories
method: get
operationId: listApertureDatasetTrajectories
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/dataset-trajectories/steps
method: get
operationId: listApertureDatasetTrajectorySteps
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/datasets/live
method: post
operationId: getApertureLiveDataset
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/stream
method: get
operationId: getApertureXidStream
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/stream/samples/{sample}/steps
method: get
operationId: listApertureXidStreamSampleSteps
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/aperture/xids/{xid}/reward-history
method: get
operationId: getApertureXidRewardHistory
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/organizations/{organization_id}/api-keys
method: get
operationId: listApiKeys
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/organizations/{organization_id}/api-keys
method: post
operationId: createApiKey
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/organizations/{organization_id}/api-keys/{key_hash}
method: delete
operationId: revokeApiKey
x-agentic-access:
action-class: acting
consequence: safety-critical
subject: required
audience: null
token:
max-ttl: 120
exchange: true
purpose-required: true
proof-of-possession: true
escalation:
human-in-the-loop: required
audit: required
- path: /api/v1/trajectories/{trajectory_id}/artifacts/content
method: post
operationId: storeTrajectoryArtifact
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/artifacts/{artifact_id}
method: get
operationId: readArtifact
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/trajectories/{trajectory_id}/artifacts
method: post
operationId: uploadTrajectoryArtifact
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/trajectories/{trajectory_id}/artifacts/{artifact_id}/complete
method: post
operationId: completeTrajectoryArtifactUpload
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/auth/me
method: get
operationId: getAuthContext
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmark-ingestion/sessions
method: post
operationId: createBenchmarkSubmissionSession
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmark-ingestion/sessions/{operation_id}/uploads
method: post
operationId: allocateBenchmarkSubmissionUploads
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmark-ingestion/sessions/{operation_id}/finalize
method: post
operationId: finalizeBenchmarkSubmission
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmark-ingestion/sessions/{operation_id}/cancel
method: post
operationId: cancelBenchmarkSubmissionSession
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmark-ingestion/operations/{operation_id}
method: get
operationId: getBenchmarkSubmissionOperation
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmark-ingestion/operations/{operation_id}/{kind}
method: get
operationId: listBenchmarkSubmissionItems
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/{bench_id}/spec
method: get
operationId: getBenchmarkSpec
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/{bench_id}/tasks
method: get
operationId: listBenchmarkSpecTasks
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/{bench_id}/task-outcomes
method: get
operationId: getBenchmarkTaskOutcomes
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/{bench_id}/tasks/{task_id}/trajectories
method: get
operationId: listBenchmarkTaskTrajectories
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/{bench_id}/tools
method: get
operationId: listBenchmarkSpecTools
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/{bench_id}/runtimes
method: get
operationId: listBenchmarkSpecRuntimes
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/{bench_id}/task-readiness
method: get
operationId: getBenchmarkTaskReadiness
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/{bench_id}/task-count
method: get
operationId: getBenchmarkTaskCount
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/uploads
method: post
operationId: createBenchmarkUpload
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmarks/{bench_id}/ingest
method: post
operationId: ingestBenchmark
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmarks/{bench_id}/tasks/diff
method: post
operationId: diffBenchmarkTasks
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmarks/{bench_id}/tasks/append
method: post
operationId: createBenchmarkTaskAppend
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmarks/{bench_id}/tasks/append/{batch_id}/commit
method: post
operationId: commitBenchmarkTaskAppend
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmarks/{bench_id}/images/build
method: post
operationId: buildBenchmarkImages
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmarks/{bench_id}/images
method: get
operationId: listBenchmarkImages
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/{bench_id}/readiness
method: get
operationId: getBenchmarkReadiness
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks
method: get
operationId: listBenchmarks
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/runtimes
method: get
operationId: listBenchmarkRuntimes
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/current
method: get
operationId: getCurrentBenchmark
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/{bench_id}
method: get
operationId: getBenchmark
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/benchmarks/{bench_id}
method: patch
operationId: updateBenchmark
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmarks/{bench_id}
method: delete
operationId: deleteBenchmark
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmarks/{bench_id}/setLatestVersion
method: post
operationId: setLatestBenchmarkVersion
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/benchmarks/{bench_id}/tasks/{task_id}
method: delete
operationId: deleteBenchmarkTask
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/billing/purchases
method: post
operationId: purchaseCredits
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: /api/v1/billing/balance
method: get
operationId: getBillingBalance
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/billing/payment-method
method: get
operationId: getBillingPaymentMethod
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/billing/payment-method/portal
method: post
operationId: openBillingPortal
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: /api/v1/billing/preferences
method: get
operationId: getBillingPreferences
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/billing/preferences
method: put
operationId: updateBillingPreferences
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/billing/preferences/fixed
method: put
operationId: updateFixedBillingPreferences
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/billing/usage
method: get
operationId: getBillingUsage
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/billing/usage/tokens
method: get
operationId: getBillingTokenUsage
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/billing/usage/spend
method: get
operationId: getBillingSpendSeries
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/billing/usage/runs
method: get
operationId: getBillingRunCosts
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/billing/notifications
method: get
operationId: getBillingNotifications
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/billing/notifications/{notification_id}/dismiss
method: post
operationId: dismissBillingNotification
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/organizations/{organization_id}/billing
method: get
operationId: getOrganizationBilling
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/organizations/{organization_id}/billing/credits
method: post
operationId: grantOrganizationCredits
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
# --- truncated at 32 KB (67 KB total) ---
# Full source: https://artifacts.apis.io/trajectory/agentic-access/trajectory-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=trajectory-agentic-access&limit=10"
curl "https://apis.io/api/v1/tags/trajectory-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.