Amazon Bedrock · Agentic Access

Amazon Bedrock Agentic Access

x-agentic-access generated

Amazon Bedrock exposes 119 API operations that an AI agent could call, of which 67 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: 52 read, 57 write, 6 physical, and 4 safety-critical.

4 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.

Artificial IntelligenceAmazon Web ServicesFoundation ModelsGenerative AILLMMachine LearningRAGAgentsResponsible AIModel Serving
Operations: 119 Acting: 67 Human-in-the-loop: 4 Method: generated

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

read 52 write 57 physical 6 safety-critical 4

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.

MethodPathConsequenceRecommended human-in-loop
POST /advanced-prompt-optimization-jobs/{jobIdentifier}/stop safety-critical required
POST /evaluation-job/{jobIdentifier}/stop safety-critical required
POST /model-customization-jobs/{jobIdentifier}/stop safety-critical required
POST /model-invocation-job/{jobIdentifier}/stop safety-critical required
POST /model-customization/custom-model-deployments physical conditional
DELETE /model-customization/custom-model-deployments/{customModelDeploymentIdentifier} physical conditional
PATCH /model-customization/custom-model-deployments/{customModelDeploymentIdentifier} physical conditional
POST /provisioned-model-throughput physical conditional
DELETE /provisioned-model-throughput/{provisionedModelId} physical conditional
PATCH /provisioned-model-throughput/{provisionedModelId} physical conditional

Source

Agentic Access

Raw ↑
generated: '2026-11-10'
method: generated
source: openapi/amazon-bedrock-advanced-prompt-optimization-jobs-api-openapi.yml, openapi/amazon-bedrock-async-invoke-api-openapi.yml,
  openapi/amazon-bedrock-automated-reasoning-policies-api-openapi.yml, openapi/amazon-bedrock-build-workflows-api-openapi.yml,
  openapi/amazon-bedrock-converse-api-openapi.yml, openapi/amazon-bedrock-custom-models-api-openapi.yml,
  openapi/amazon-bedrock-enforcedguardrailsconfiguration-api-openapi.yml, openapi/amazon-bedrock-evaluation-jobs-api-openapi.yml,
  openapi/amazon-bedrock-foundation-models-api-openapi.yml, openapi/amazon-bedrock-guardrails-api-openapi.yml,
  openapi/amazon-bedrock-imported-models-api-openapi.yml, openapi/amazon-bedrock-inference-api-openapi.yml,
  openapi/amazon-bedrock-inference-profiles-api-openapi.yml, openapi/amazon-bedrock-logging-api-openapi.yml,
  openapi/amazon-bedrock-marketplace-model-api-openapi.yml, openapi/amazon-bedrock-model-copy-jobs-api-openapi.yml,
  openapi/amazon-bedrock-model-customization-api-openapi.yml, openapi/amazon-bedrock-model-import-jobs-api-openapi.yml,
  openapi/amazon-bedrock-operations-api-openapi.yml, openapi/amazon-bedrock-prompt-routers-api-openapi.yml,
  openapi/amazon-bedrock-provisioned-model-throughput-api-openapi.yml, openapi/amazon-bedrock-provisioned-throughput-api-openapi.yml,
  openapi/amazon-bedrock-resource-policy-api-openapi.yml, openapi/amazon-bedrock-stop-api-openapi.yml,
  openapi/amazon-bedrock-test-cases-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: 119
  by_action_class:
    acting: 67
    connected: 52
  by_consequence:
    write: 57
    read: 52
    physical: 6
    safety-critical: 4
  human_in_the_loop_required: 4
operations:
- path: /advanced-prompt-optimization-jobs
  method: post
  operationId: CreateAdvancedPromptOptimizationJob
  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: /advanced-prompt-optimization-jobs
  method: get
  operationId: ListAdvancedPromptOptimizationJobs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /advanced-prompt-optimization-jobs/{jobIdentifier}
  method: get
  operationId: GetAdvancedPromptOptimizationJob
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /async-invoke/{invocationArn}
  method: get
  operationId: GetAsyncInvoke
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /async-invoke
  method: get
  operationId: ListAsyncInvokes
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /async-invoke
  method: post
  operationId: StartAsyncInvoke
  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: /automated-reasoning-policies
  method: post
  operationId: CreateAutomatedReasoningPolicy
  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: /automated-reasoning-policies
  method: get
  operationId: ListAutomatedReasoningPolicies
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /automated-reasoning-policies/{policyArn}
  method: get
  operationId: GetAutomatedReasoningPolicy
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /automated-reasoning-policies/{policyArn}
  method: patch
  operationId: UpdateAutomatedReasoningPolicy
  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: /automated-reasoning-policies/{policyArn}
  method: delete
  operationId: DeleteAutomatedReasoningPolicy
  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: /automated-reasoning-policies/{policyArn}/build-workflows/{buildWorkflowId}
  method: delete
  operationId: DeleteAutomatedReasoningPolicyBuildWorkflow
  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: /automated-reasoning-policies/{policyArn}/build-workflows/{buildWorkflowId}
  method: get
  operationId: GetAutomatedReasoningPolicyBuildWorkflow
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /automated-reasoning-policies/{policyArn}/build-workflows
  method: get
  operationId: ListAutomatedReasoningPolicyBuildWorkflows
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /model/{modelId}/converse
  method: post
  operationId: Converse
  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: /model/{modelId}/converse-stream
  method: post
  operationId: ConverseStream
  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: /custom-models/create-custom-model
  method: post
  operationId: CreateCustomModel
  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: /custom-models/{modelIdentifier}
  method: delete
  operationId: DeleteCustomModel
  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: /custom-models/{modelIdentifier}
  method: get
  operationId: GetCustomModel
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /custom-models
  method: get
  operationId: ListCustomModels
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /enforcedGuardrailsConfiguration/{configId}
  method: delete
  operationId: DeleteEnforcedGuardrailConfiguration
  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: /enforcedGuardrailsConfiguration
  method: get
  operationId: ListEnforcedGuardrailsConfiguration
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /enforcedGuardrailsConfiguration
  method: put
  operationId: PutEnforcedGuardrailConfiguration
  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: /evaluation-jobs/batch-delete
  method: post
  operationId: BatchDeleteEvaluationJob
  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: /evaluation-jobs
  method: post
  operationId: CreateEvaluationJob
  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: /evaluation-jobs
  method: get
  operationId: ListEvaluationJobs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /evaluation-jobs/{jobIdentifier}
  method: get
  operationId: GetEvaluationJob
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /foundation-models/{modelIdentifier}
  method: get
  operationId: GetFoundationModel
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /foundation-models
  method: get
  operationId: ListFoundationModels
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /guardrails/{guardrailIdentifier}
  method: post
  operationId: CreateGuardrailVersion
  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: /guardrails/{guardrailIdentifier}
  method: get
  operationId: GetGuardrail
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /guardrails/{guardrailIdentifier}
  method: put
  operationId: UpdateGuardrail
  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: /guardrails/{guardrailIdentifier}
  method: delete
  operationId: DeleteGuardrail
  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: /guardrails
  method: post
  operationId: CreateGuardrail
  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: /guardrails
  method: get
  operationId: ListGuardrails
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /imported-models/{modelIdentifier}
  method: delete
  operationId: DeleteImportedModel
  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: /imported-models/{modelIdentifier}
  method: get
  operationId: GetImportedModel
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /imported-models
  method: get
  operationId: ListImportedModels
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /model/{modelId}/invoke
  method: post
  operationId: InvokeModel
  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: /model/{modelId}/invoke-with-response-stream
  method: post
  operationId: InvokeModelWithResponseStream
  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: /inference-profiles
  method: post
  operationId: CreateInferenceProfile
  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: /inference-profiles
  method: get
  operationId: ListInferenceProfiles
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /inference-profiles/{inferenceProfileIdentifier}
  method: get
  operationId: GetInferenceProfile
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /inference-profiles/{inferenceProfileIdentifier}
  method: delete
  operationId: DeleteInferenceProfile
  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: /logging/modelinvocations
  method: delete
  operationId: DeleteModelInvocationLoggingConfiguration
  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: /logging/modelinvocations
  method: get
  operationId: GetModelInvocationLoggingConfiguration
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /logging/modelinvocations
  method: put
  operationId: PutModelInvocationLoggingConfiguration
  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: /marketplace-model/endpoints
  method: post
  operationId: CreateMarketplaceModelEndpoint
  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: /marketplace-model/endpoints
  method: get
  operationId: ListMarketplaceModelEndpoints
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /marketplace-model/endpoints/{endpointArn}
  method: delete
  operationId: DeleteMarketplaceModelEndpoint
  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: /marketplace-model/endpoints/{endpointArn}
  method: get
  operationId: GetMarketplaceModelEndpoint
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /marketplace-model/endpoints/{endpointArn}
  method: patch
  operationId: UpdateMarketplaceModelEndpoint
  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: /model-copy-jobs
  method: post
  operationId: CreateModelCopyJob
  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: /model-copy-jobs
  method: get
  operationId: ListModelCopyJobs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /model-copy-jobs/{jobArn}
  method: get
  operationId: GetModelCopyJob
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /model-customization/custom-model-deployments
  method: post
  operationId: CreateCustomModelDeployment
  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: /model-customization/custom-model-deployments
  method: get
  operationId: ListCustomModelDeployments
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /model-customization/custom-model-deployments/{customModelDeploymentIdentifier}
  method: delete
  operationId: DeleteCustomModelDeployment
  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: /model-customization/custom-model-deployments/{customModelDeploymentIdentifier}
  method: get
  operationId: GetCustomModelDeployment
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /model-customization/custom-model-deployments/{customModelDeploymentIdentifier}
  method: patch
  operationId: UpdateCustomModelDeployment
  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: /model-customization-jobs
  method: post
  operationId: CreateModelCustomizationJob
  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: /model-customization-jobs
  method: get
  operationId: ListModelCustomizationJobs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /model-customization-jobs/{jobIdentifier}
  method: get
  operationId: GetModelCustomizationJob
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /model-import-jobs
  method: post
  operationId: CreateModelImportJob
  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: /model-import-jobs
  method: get
  operationId: ListModelImportJobs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /model-import-jobs/{jobIdentifier}
  method: get
  operationId: GetModelImportJob
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /advanced-prompt-optimization-job/batch-delete
  method: post
  operationId: BatchDeleteAdvancedPromptOptimizationJob
  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: /use-case-for-model-access
  method: get
  operationId: GetUseCaseForModelAccess
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /use-case-for-model-access
  method: post
  operationId: PutUseCaseForModelAccess
  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: /automated-reasoning-policies/{policyArn}/build-workflows/{buildWorkflowId}/cancel
  method: post
  operationId: CancelAutomatedReasoningPolicyBuildWorkflow
  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: /automated-reasoning-policies/{policyArn}/versions
  method: post
  operationId: CreateAutomatedReasoningPolicyVersion
  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: /automated-reasoning-policies/{policyArn}/export
  method: get
  operationId: ExportAutomatedReasoningPolicyVersion
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /automated-reasoning-policies/{policyArn}/build-workflows/{buildWorkflowId}/annotations
  method: get
  operationId: GetAutomatedReasoningPolicyAnnotations
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /automated-reasoning-policies/{policyArn}/build-workflows/{buildWorkflowId}/annotations
  method: patch
  operationId: UpdateAutomatedReasoningPolicyAnnotations
  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: /automated-reasoning-policies/{policyArn}/build-workflows/{buildWorkflowId}/result-assets
  method: get
  operationId: GetAutomatedReasoningPolicyBuildWorkflowResultAssets
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /automated-reasoning-policies/{policyArn}/build-workflows/{buildWorkflowId}/scenarios
  method: get
  operationId: GetAutomatedReasoningPolicyNextScenario
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /automated-reasoning-policies/{policyArn}/build-workflows/{buildWorkflowId}/test-cases/{testCaseId}/test-results
  method: get
  operationId: GetAutomatedReasoningPolicyTestResult
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /automated-reasoning-policies/{policyArn}/build-workflows/{buildWorkflowId}/test-results
  method: get
  operationId: ListAutomatedReasoningPolicyTestResults
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /automated-reasoning-policies/{policyArn}/build-workflows/{buildWorkflowType}/start
  method: post
  operationId: StartAutomatedReasoningPolicyBuildWorkflow
  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: /automated-reasoning-policies/{policyArn}/build-workflows/{buildWorkflowId}/test-workflows
  method: post
  operationId: StartAutomatedReasoningPolicyTestWorkflow
  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: /marketplace-model/endpoints/{endpointArn}/registration
  method: delete
  operationId: DeregisterMarketplaceModelEndpoint
  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: /marketplace-model/endpoints/{endpointIdentifier}/registration
  method: post
  operationId: RegisterMarketplaceModelEndpoint
  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: /data-retention
  method: get
  operationId: GetAccountDataRetention
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /data-retention
  method: put
  operationId: PutAccountDataRetention
  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: /model-invocation-job
  method: post
  operationId: CreateModelInvocationJob
  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: /model-invocation-job/{jobIdentifier}
  method: get
  operationId: GetModelInvocationJob
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /model-invocation-jobs
  method: get
  operationId: ListModelInvocationJobs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /create-foundation-model-agreement
  method: post
  operationId: CreateFoundationModelAgreement
  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: /delete-foundation-model-agreement
  method: post
  operationId: DeleteFoundationModelAgreement
  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: /foundation-model-availability/{modelId}
  method: get
  operationId: GetFoundationModelAvailability
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /list-foundation-model-agreement-offers/{modelId}
  method: get
  operationId: ListFoundationModelAgreementOffers
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /listTagsForResource
  method: post
  operationId: ListTagsForResource
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /tagResource
  method: post
  operationId: TagResource
  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: /untagResource
  method: post
  operationId: UntagResource
  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: /guardrail/{guardrailIdentifier}/version/{guardrailVersion}/apply
  method: post
  operationId: ApplyGuardrail
  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: /guardrail-checks/invoke
  method: post
  operationId: InvokeGuardrailChecks
  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: /model/{modelId}/invoke-with-bidirectional-stream
  method: post
  operationId: InvokeModelWithBidirectionalStream
  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: /model/{modelId}/count-tokens
  method: post
  operationId: CountTokens
  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 (38 KB total) ---
# Full source: https://artifacts.apis.io/amazon-bedrock/agentic-access/amazon-bedrock-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=amazon-bedrock-agentic-access&limit=10"
Everything under a tag
curl "https://apis.io/api/v1/tags/amazon-bedrock-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.