Configure your Splunk Observability Cloud account to collect Amazon Bedrock AgentCore Gateway metrics
Configure your Splunk Observability Cloud account to collect Amazon Bedrock AgentCore Gateway metrics.
You can monitor the performance of your Amazon Bedrock AgentCore Gateway instance by configuring Amazon Bedrock AgentCore Gateway to send metrics to Splunk Observability Cloud. This solution creates a cloud connection in your Splunk Observability Cloud account that collects metrics from AWS CloudWatch.
Complete the following steps to collect metrics from Amazon Bedrock AgentCore Gateway.
Metrics
The following metrics are available for Amazon Bedrock AgentCore Gateway. For more information on these metrics, see AgentCore generated gateway observability data in the AWS documentation and View organization metrics for Splunk Observability Cloud.
These metrics are considered custom metrics in Splunk Observability Cloud.
| Metric name | Unit | Description |
|---|---|---|
Invocations |
count | The total number of requests made to each Data Plane API. Each API call counts as one invocation regardless of the response status. |
Throttles |
count | The number of requests throttled (status code 429) by the service. |
SystemErrors |
count | The number of requests that failed with a 5xx status code. |
UserErrors |
count | The number of requests that failed with a 4xx status code, except 429. |
Latency |
milliseconds | The time elapsed between when the service receives the request and when it begins sending the first response token. In other words, the initial response time. |
Duration |
milliseconds | The total time elapsed between receiving the request and sending the final response token. Represents complete end-to-end processing time of the request. |
TargetExecutionTime |
milliseconds | The total time taken to execute the target over Lambda/OpenAPI/etc. This metric helps determine the contribution of the target to the total latency. |
Attributes
Amazon metrics are shared across multiple Amazon entities and differentiated with the namespace attribute.
| Attribute name | Description |
|---|---|
AWSUniqueId |
A globally unique identifier assigned by AWS to the gateway resource. |
Method |
Represents the MCP route or action path used to invoke a capability on the gateway. |
namespace |
Logical scope used to group and isolate target resources and operations. |
Operation |
Defines the logical operation run by the gateway for the incoming request. |
Protocol |
Specifies the communication protocol used by the gateway. |
Resource |
Represents the source entity from which metrics are generated. |
TargetType |
Represents the type of backend associated with the tool. For example, LAMBDA or API_GATEWAY. |
Next steps
After you set up data collection, the data populates built-in dashboards that you can use to monitor and troubleshoot your instances.
For more information on using built-in dashboards in Splunk Observability Cloud, see: