BedrockAgentCoreControlClient

Welcome to the Amazon Bedrock AgentCore Control plane API reference. Control plane actions configure, create, modify, and monitor Amazon Web Services resources.

Types

Link copied to clipboard
class Builder
Link copied to clipboard
object Companion
Link copied to clipboard
class Config

Properties

Link copied to clipboard

BedrockAgentCoreControlClient's configuration

Functions

Link copied to clipboard

Creates an Amazon Bedrock AgentCore Runtime.

Link copied to clipboard

Creates an AgentCore Runtime endpoint.

Link copied to clipboard

Creates a new API key credential provider.

Link copied to clipboard

Creates a custom browser.

Link copied to clipboard

Creates a custom code interpreter.

Link copied to clipboard

Creates a custom evaluator for agent quality assessment. Custom evaluators use LLM-as-a-Judge configurations with user-defined prompts, rating scales, and model settings to evaluate agent performance at tool call, trace, or session levels.

Link copied to clipboard

Creates a gateway for Amazon Bedrock Agent. A gateway serves as an integration point between your agent and external services.

Link copied to clipboard

Creates a target for a gateway. A target defines an endpoint that the gateway can connect to.

Link copied to clipboard

Creates a new Amazon Bedrock AgentCore Memory resource.

Link copied to clipboard

Creates a new OAuth2 credential provider.

Link copied to clipboard

Creates an online evaluation configuration for continuous monitoring of agent performance. Online evaluation automatically samples live traffic from CloudWatch logs at specified rates and applies evaluators to assess agent quality in production.

Link copied to clipboard

Creates a policy within the AgentCore Policy system. Policies provide real-time, deterministic control over agentic interactions with AgentCore Gateway. Using the Cedar policy language, you can define fine-grained policies that specify which interactions with Gateway tools are permitted based on input parameters and OAuth claims, ensuring agents operate within defined boundaries and business rules. The policy is validated during creation against the Cedar schema generated from the Gateway's tools' input schemas, which defines the available tools, their parameters, and expected data types. This is an asynchronous operation. Use the GetPolicy operation to poll the status field to track completion.

Link copied to clipboard

Creates a new policy engine within the AgentCore Policy system. A policy engine is a collection of policies that evaluates and authorizes agent tool calls. When associated with Gateways (each Gateway can be associated with at most one policy engine, but multiple Gateways can be associated with the same engine), the policy engine intercepts all agent requests and determines whether to allow or deny each action based on the defined policies. This is an asynchronous operation. Use the GetPolicyEngine operation to poll the status field to track completion.

Link copied to clipboard

Creates a new workload identity.

Link copied to clipboard

Deletes an Amazon Bedrock AgentCore Runtime.

Link copied to clipboard

Deletes an AAgentCore Runtime endpoint.

Link copied to clipboard

Deletes an API key credential provider.

Link copied to clipboard

Deletes a custom browser.

Link copied to clipboard

Deletes a custom code interpreter.

Link copied to clipboard

Deletes a custom evaluator. Builtin evaluators cannot be deleted. The evaluator must not be referenced by any active online evaluation configurations.

Link copied to clipboard

Deletes a gateway.

Link copied to clipboard

Deletes a gateway target.

Link copied to clipboard

Deletes an Amazon Bedrock AgentCore Memory resource.

Link copied to clipboard

Deletes an OAuth2 credential provider.

Link copied to clipboard

Deletes an online evaluation configuration and stops any ongoing evaluation processes associated with it.

Link copied to clipboard

Deletes an existing policy from the AgentCore Policy system. Once deleted, the policy can no longer be used for agent behavior control and all references to it become invalid. This is an asynchronous operation. Use the GetPolicy operation to poll the status field to track completion.

Link copied to clipboard

Deletes an existing policy engine from the AgentCore Policy system. The policy engine must not have any associated policies before deletion. Once deleted, the policy engine and all its configurations become unavailable for policy management and evaluation. This is an asynchronous operation. Use the GetPolicyEngine operation to poll the status field to track completion.

Link copied to clipboard

Deletes the resource-based policy for a specified resource.

Link copied to clipboard

Deletes a workload identity.

Link copied to clipboard

Gets an Amazon Bedrock AgentCore Runtime.

Link copied to clipboard

Gets information about an Amazon Secure AgentEndpoint.

Link copied to clipboard

Retrieves information about an API key credential provider.

Link copied to clipboard
abstract suspend fun getBrowser(input: GetBrowserRequest): GetBrowserResponse

Gets information about a custom browser.

Link copied to clipboard

Gets information about a custom code interpreter.

Link copied to clipboard

Retrieves detailed information about an evaluator, including its configuration, status, and metadata. Works with both built-in and custom evaluators.

Link copied to clipboard
abstract suspend fun getGateway(input: GetGatewayRequest): GetGatewayResponse

Retrieves information about a specific Gateway.

Link copied to clipboard

Retrieves information about a specific gateway target.

Link copied to clipboard
abstract suspend fun getMemory(input: GetMemoryRequest): GetMemoryResponse

Retrieve an existing Amazon Bedrock AgentCore Memory resource.

Link copied to clipboard

Retrieves information about an OAuth2 credential provider.

Link copied to clipboard

Retrieves detailed information about an online evaluation configuration, including its rules, data sources, evaluators, and execution status.

Link copied to clipboard
abstract suspend fun getPolicy(input: GetPolicyRequest): GetPolicyResponse

Retrieves detailed information about a specific policy within the AgentCore Policy system. This operation returns the complete policy definition, metadata, and current status, allowing administrators to review and manage policy configurations.

Link copied to clipboard

Retrieves detailed information about a specific policy engine within the AgentCore Policy system. This operation returns the complete policy engine configuration, metadata, and current status, allowing administrators to review and manage policy engine settings.

Link copied to clipboard

Retrieves information about a policy generation request within the AgentCore Policy system. Policy generation converts natural language descriptions into Cedar policy statements using AI-powered translation, enabling non-technical users to create policies.

Link copied to clipboard

Retrieves the resource-based policy for a specified resource.

Link copied to clipboard
abstract suspend fun getTokenVault(input: GetTokenVaultRequest = GetTokenVaultRequest { }): GetTokenVaultResponse

Retrieves information about a token vault.

Link copied to clipboard

Retrieves information about a workload identity.

Link copied to clipboard

Lists all endpoints for a specific Amazon Secure Agent.

Link copied to clipboard
abstract suspend fun listAgentRuntimes(input: ListAgentRuntimesRequest = ListAgentRuntimesRequest { }): ListAgentRuntimesResponse

Lists all Amazon Secure Agents in your account.

Link copied to clipboard

Lists all versions of a specific Amazon Secure Agent.

Link copied to clipboard
abstract suspend fun listApiKeyCredentialProviders(input: ListApiKeyCredentialProvidersRequest = ListApiKeyCredentialProvidersRequest { }): ListApiKeyCredentialProvidersResponse

Lists all API key credential providers in your account.

Link copied to clipboard
abstract suspend fun listBrowsers(input: ListBrowsersRequest = ListBrowsersRequest { }): ListBrowsersResponse

Lists all custom browsers in your account.

Link copied to clipboard
abstract suspend fun listCodeInterpreters(input: ListCodeInterpretersRequest = ListCodeInterpretersRequest { }): ListCodeInterpretersResponse

Lists all custom code interpreters in your account.

Link copied to clipboard
abstract suspend fun listEvaluators(input: ListEvaluatorsRequest = ListEvaluatorsRequest { }): ListEvaluatorsResponse

Lists all available evaluators, including both builtin evaluators provided by the service and custom evaluators created by the user.

Link copied to clipboard
abstract suspend fun listGateways(input: ListGatewaysRequest = ListGatewaysRequest { }): ListGatewaysResponse

Lists all gateways in the account.

Link copied to clipboard

Lists all targets for a specific gateway.

Link copied to clipboard
abstract suspend fun listMemories(input: ListMemoriesRequest = ListMemoriesRequest { }): ListMemoriesResponse

Lists the available Amazon Bedrock AgentCore Memory resources in the current Amazon Web Services Region.

Link copied to clipboard
abstract suspend fun listOauth2CredentialProviders(input: ListOauth2CredentialProvidersRequest = ListOauth2CredentialProvidersRequest { }): ListOauth2CredentialProvidersResponse

Lists all OAuth2 credential providers in your account.

Link copied to clipboard
abstract suspend fun listOnlineEvaluationConfigs(input: ListOnlineEvaluationConfigsRequest = ListOnlineEvaluationConfigsRequest { }): ListOnlineEvaluationConfigsResponse

Lists all online evaluation configurations in the account, providing summary information about each configuration's status and settings.

Link copied to clipboard

Retrieves a list of policies within the AgentCore Policy engine. This operation supports pagination and filtering to help administrators manage and discover policies across policy engines. Results can be filtered by policy engine or resource associations.

Link copied to clipboard
abstract suspend fun listPolicyEngines(input: ListPolicyEnginesRequest = ListPolicyEnginesRequest { }): ListPolicyEnginesResponse

Retrieves a list of policy engines within the AgentCore Policy system. This operation supports pagination to help administrators discover and manage policy engines across their account. Each policy engine serves as a container for related policies.

Link copied to clipboard

Retrieves a list of generated policy assets from a policy generation request within the AgentCore Policy system. This operation returns the actual Cedar policies and related artifacts produced by the AI-powered policy generation process, allowing users to review and select from multiple generated policy options.

Link copied to clipboard

Retrieves a list of policy generation requests within the AgentCore Policy system. This operation supports pagination and filtering to help track and manage AI-powered policy generation operations.

Link copied to clipboard

Lists the tags associated with the specified resource.

Link copied to clipboard
abstract suspend fun listWorkloadIdentities(input: ListWorkloadIdentitiesRequest = ListWorkloadIdentitiesRequest { }): ListWorkloadIdentitiesResponse

Lists all workload identities in your account.

Link copied to clipboard

Creates or updates a resource-based policy for a resource with the specified resourceArn.

Link copied to clipboard

Sets the customer master key (CMK) for a token vault.

Link copied to clipboard

Initiates the AI-powered generation of Cedar policies from natural language descriptions within the AgentCore Policy system. This feature enables both technical and non-technical users to create policies by describing their authorization requirements in plain English, which is then automatically translated into formal Cedar policy statements. The generation process analyzes the natural language input along with the Gateway's tool context to produce validated policy options. Generated policy assets are automatically deleted after 7 days, so you should review and create policies from the generated assets within this timeframe. Once created, policies are permanent and not subject to this expiration. Generated policies should be reviewed and tested in log-only mode before deploying to production. Use this when you want to describe policy intent naturally rather than learning Cedar syntax, though generated policies may require refinement for complex scenarios.

Link copied to clipboard
Link copied to clipboard
abstract suspend fun tagResource(input: TagResourceRequest): TagResourceResponse

Associates the specified tags to a resource with the specified resourceArn. If existing tags on a resource are not specified in the request parameters, they are not changed. When a resource is deleted, the tags associated with that resource are also deleted.

Link copied to clipboard

Removes the specified tags from the specified resource.

Link copied to clipboard

Updates an existing Amazon Secure Agent.

Link copied to clipboard

Updates an existing Amazon Bedrock AgentCore Runtime endpoint.

Link copied to clipboard

Updates an existing API key credential provider.

Link copied to clipboard

Updates a custom evaluator's configuration, description, or evaluation level. Built-in evaluators cannot be updated. The evaluator must not be locked for modification.

Link copied to clipboard

Updates an existing gateway.

Link copied to clipboard

Updates an existing gateway target.

Link copied to clipboard

Update an Amazon Bedrock AgentCore Memory resource memory.

Link copied to clipboard

Updates an existing OAuth2 credential provider.

Link copied to clipboard

Updates an online evaluation configuration's settings, including rules, data sources, evaluators, and execution status. Changes take effect immediately for ongoing evaluations.

Link copied to clipboard

Updates an existing policy within the AgentCore Policy system. This operation allows modification of the policy description and definition while maintaining the policy's identity. The updated policy is validated against the Cedar schema before being applied. This is an asynchronous operation. Use the GetPolicy operation to poll the status field to track completion.

Link copied to clipboard

Updates an existing policy engine within the AgentCore Policy system. This operation allows modification of the policy engine description while maintaining its identity. This is an asynchronous operation. Use the GetPolicyEngine operation to poll the status field to track completion.

Link copied to clipboard

Updates an existing workload identity.

Inherited functions

Link copied to clipboard

Creates an Amazon Bedrock AgentCore Runtime.

Link copied to clipboard
Link copied to clipboard
Link copied to clipboard

Creates a custom browser.

Link copied to clipboard

Creates a custom code interpreter.

Link copied to clipboard

Creates a custom evaluator for agent quality assessment. Custom evaluators use LLM-as-a-Judge configurations with user-defined prompts, rating scales, and model settings to evaluate agent performance at tool call, trace, or session levels.

Link copied to clipboard

Creates a gateway for Amazon Bedrock Agent. A gateway serves as an integration point between your agent and external services.

Link copied to clipboard

Creates a target for a gateway. A target defines an endpoint that the gateway can connect to.

Link copied to clipboard

Creates a new Amazon Bedrock AgentCore Memory resource.

Link copied to clipboard
Link copied to clipboard

Creates an online evaluation configuration for continuous monitoring of agent performance. Online evaluation automatically samples live traffic from CloudWatch logs at specified rates and applies evaluators to assess agent quality in production.

Link copied to clipboard

Creates a policy within the AgentCore Policy system. Policies provide real-time, deterministic control over agentic interactions with AgentCore Gateway. Using the Cedar policy language, you can define fine-grained policies that specify which interactions with Gateway tools are permitted based on input parameters and OAuth claims, ensuring agents operate within defined boundaries and business rules. The policy is validated during creation against the Cedar schema generated from the Gateway's tools' input schemas, which defines the available tools, their parameters, and expected data types. This is an asynchronous operation. Use the GetPolicy operation to poll the status field to track completion.

Link copied to clipboard

Creates a new policy engine within the AgentCore Policy system. A policy engine is a collection of policies that evaluates and authorizes agent tool calls. When associated with Gateways (each Gateway can be associated with at most one policy engine, but multiple Gateways can be associated with the same engine), the policy engine intercepts all agent requests and determines whether to allow or deny each action based on the defined policies. This is an asynchronous operation. Use the GetPolicyEngine operation to poll the status field to track completion.

Link copied to clipboard

Creates a new workload identity.

Link copied to clipboard

Deletes an Amazon Bedrock AgentCore Runtime.

Link copied to clipboard
Link copied to clipboard

Deletes a custom browser.

Link copied to clipboard

Deletes a custom code interpreter.

Link copied to clipboard

Deletes a custom evaluator. Builtin evaluators cannot be deleted. The evaluator must not be referenced by any active online evaluation configurations.

Link copied to clipboard

Deletes a gateway.

Link copied to clipboard
Link copied to clipboard

Deletes an Amazon Bedrock AgentCore Memory resource.

Link copied to clipboard

Deletes an online evaluation configuration and stops any ongoing evaluation processes associated with it.

Link copied to clipboard

Deletes an existing policy from the AgentCore Policy system. Once deleted, the policy can no longer be used for agent behavior control and all references to it become invalid. This is an asynchronous operation. Use the GetPolicy operation to poll the status field to track completion.

Link copied to clipboard

Deletes an existing policy engine from the AgentCore Policy system. The policy engine must not have any associated policies before deletion. Once deleted, the policy engine and all its configurations become unavailable for policy management and evaluation. This is an asynchronous operation. Use the GetPolicyEngine operation to poll the status field to track completion.

Link copied to clipboard

Deletes the resource-based policy for a specified resource.

Link copied to clipboard
Link copied to clipboard

Gets an Amazon Bedrock AgentCore Runtime.

Link copied to clipboard

Gets information about an Amazon Secure AgentEndpoint.

Link copied to clipboard

Retrieves information about an API key credential provider.

Link copied to clipboard

Gets information about a custom browser.

Link copied to clipboard

Gets information about a custom code interpreter.

Link copied to clipboard

Retrieves detailed information about an evaluator, including its configuration, status, and metadata. Works with both built-in and custom evaluators.

Link copied to clipboard

Retrieves information about a specific Gateway.

Link copied to clipboard

Retrieves information about a specific gateway target.

Link copied to clipboard

Retrieve an existing Amazon Bedrock AgentCore Memory resource.

Link copied to clipboard

Retrieves information about an OAuth2 credential provider.

Link copied to clipboard

Retrieves detailed information about an online evaluation configuration, including its rules, data sources, evaluators, and execution status.

Link copied to clipboard

Retrieves detailed information about a specific policy within the AgentCore Policy system. This operation returns the complete policy definition, metadata, and current status, allowing administrators to review and manage policy configurations.

Link copied to clipboard

Retrieves detailed information about a specific policy engine within the AgentCore Policy system. This operation returns the complete policy engine configuration, metadata, and current status, allowing administrators to review and manage policy engine settings.

Link copied to clipboard

Retrieves information about a policy generation request within the AgentCore Policy system. Policy generation converts natural language descriptions into Cedar policy statements using AI-powered translation, enabling non-technical users to create policies.

Link copied to clipboard

Retrieves the resource-based policy for a specified resource.

Link copied to clipboard

Retrieves information about a token vault.

Link copied to clipboard

Retrieves information about a workload identity.

Link copied to clipboard

Lists all endpoints for a specific Amazon Secure Agent.

Link copied to clipboard

Lists all Amazon Secure Agents in your account.

Link copied to clipboard

Lists all versions of a specific Amazon Secure Agent.

Link copied to clipboard

Lists all API key credential providers in your account.

Link copied to clipboard

Lists all custom browsers in your account.

Link copied to clipboard

Lists all custom code interpreters in your account.

Link copied to clipboard

Lists all available evaluators, including both builtin evaluators provided by the service and custom evaluators created by the user.

Link copied to clipboard

Lists all gateways in the account.

Link copied to clipboard

Lists all targets for a specific gateway.

Link copied to clipboard

Lists the available Amazon Bedrock AgentCore Memory resources in the current Amazon Web Services Region.

Link copied to clipboard

Lists all OAuth2 credential providers in your account.

Link copied to clipboard

Lists all online evaluation configurations in the account, providing summary information about each configuration's status and settings.

Link copied to clipboard

Retrieves a list of policies within the AgentCore Policy engine. This operation supports pagination and filtering to help administrators manage and discover policies across policy engines. Results can be filtered by policy engine or resource associations.

Link copied to clipboard

Retrieves a list of policy engines within the AgentCore Policy system. This operation supports pagination to help administrators discover and manage policy engines across their account. Each policy engine serves as a container for related policies.

Link copied to clipboard

Retrieves a list of generated policy assets from a policy generation request within the AgentCore Policy system. This operation returns the actual Cedar policies and related artifacts produced by the AI-powered policy generation process, allowing users to review and select from multiple generated policy options.

Link copied to clipboard

Retrieves a list of policy generation requests within the AgentCore Policy system. This operation supports pagination and filtering to help track and manage AI-powered policy generation operations.

Link copied to clipboard

Lists the tags associated with the specified resource.

Link copied to clipboard

Lists all workload identities in your account.

Link copied to clipboard

Creates or updates a resource-based policy for a resource with the specified resourceArn.

Link copied to clipboard

Sets the customer master key (CMK) for a token vault.

Link copied to clipboard

Initiates the AI-powered generation of Cedar policies from natural language descriptions within the AgentCore Policy system. This feature enables both technical and non-technical users to create policies by describing their authorization requirements in plain English, which is then automatically translated into formal Cedar policy statements. The generation process analyzes the natural language input along with the Gateway's tool context to produce validated policy options. Generated policy assets are automatically deleted after 7 days, so you should review and create policies from the generated assets within this timeframe. Once created, policies are permanent and not subject to this expiration. Generated policies should be reviewed and tested in log-only mode before deploying to production. Use this when you want to describe policy intent naturally rather than learning Cedar syntax, though generated policies may require refinement for complex scenarios.

Link copied to clipboard

Associates the specified tags to a resource with the specified resourceArn. If existing tags on a resource are not specified in the request parameters, they are not changed. When a resource is deleted, the tags associated with that resource are also deleted.

Link copied to clipboard

Removes the specified tags from the specified resource.

Link copied to clipboard

Updates an existing Amazon Secure Agent.

Link copied to clipboard

Updates an existing Amazon Bedrock AgentCore Runtime endpoint.

Link copied to clipboard

Updates an existing API key credential provider.

Link copied to clipboard

Updates a custom evaluator's configuration, description, or evaluation level. Built-in evaluators cannot be updated. The evaluator must not be locked for modification.

Link copied to clipboard

Updates an existing gateway.

Link copied to clipboard

Updates an existing gateway target.

Link copied to clipboard

Update an Amazon Bedrock AgentCore Memory resource memory.

Link copied to clipboard
Link copied to clipboard

Updates an online evaluation configuration's settings, including rules, data sources, evaluators, and execution status. Changes take effect immediately for ongoing evaluations.

Link copied to clipboard

Updates an existing policy within the AgentCore Policy system. This operation allows modification of the policy description and definition while maintaining the policy's identity. The updated policy is validated against the Cedar schema before being applied. This is an asynchronous operation. Use the GetPolicy operation to poll the status field to track completion.

Link copied to clipboard

Updates an existing policy engine within the AgentCore Policy system. This operation allows modification of the policy engine description while maintaining its identity. This is an asynchronous operation. Use the GetPolicyEngine operation to poll the status field to track completion.

Link copied to clipboard

Updates an existing workload identity.

Link copied to clipboard
suspend fun BedrockAgentCoreControlClient.waitUntilMemoryCreated(request: GetMemoryRequest, retryStrategy: <Error class: unknown class>? = null): <Error class: unknown class><GetMemoryResponse>
Link copied to clipboard
suspend fun BedrockAgentCoreControlClient.waitUntilPolicyActive(request: GetPolicyRequest, retryStrategy: <Error class: unknown class>? = null): <Error class: unknown class><GetPolicyResponse>

Wait until a Policy is active

Link copied to clipboard
suspend fun BedrockAgentCoreControlClient.waitUntilPolicyDeleted(request: GetPolicyRequest, retryStrategy: <Error class: unknown class>? = null): <Error class: unknown class><GetPolicyResponse>

Wait until a Policy is deleted

Link copied to clipboard
suspend fun BedrockAgentCoreControlClient.waitUntilPolicyEngineActive(request: GetPolicyEngineRequest, retryStrategy: <Error class: unknown class>? = null): <Error class: unknown class><GetPolicyEngineResponse>

Wait until a PolicyEngine is active

Link copied to clipboard
suspend fun BedrockAgentCoreControlClient.waitUntilPolicyEngineDeleted(request: GetPolicyEngineRequest, retryStrategy: <Error class: unknown class>? = null): <Error class: unknown class><GetPolicyEngineResponse>

Wait until a PolicyEngine is deleted

Link copied to clipboard
suspend fun BedrockAgentCoreControlClient.waitUntilPolicyGenerationCompleted(request: GetPolicyGenerationRequest, retryStrategy: <Error class: unknown class>? = null): <Error class: unknown class><GetPolicyGenerationResponse>

Wait until policy generation is completed

Link copied to clipboard

Create a copy of the client with one or more configuration values overridden. This method allows the caller to perform scoped config overrides for one or more client operations.