What can you do with the Amazon CloudWatch integration?

LiveContext exposes 30 operations on Amazon CloudWatch, covering metric stream, dashboard, alarm and anomaly detector. Common uses include automate dashboard management, automate alarm management and describe alarm programmatically.

LiveContext

All integrations

Amazon CloudWatch integration

AWS CloudWatch monitoring and observability API for collecting metrics, setting alarms, and monitoring AWS resources. Query metrics, manage alarms, retrieve logs, and create dashboards for infrastructure monitoring.

30 toolsCustom authAPI docs

Connect Amazon CloudWatch How integrations work

Common Amazon CloudWatch use cases

automate dashboard management
automate alarm management
describe alarm programmatically
automate resource management
automate metric data management
automate alarm action management
automate anomaly detector management
remove metric stream
list tag programmatically
embed metric chart in report

What you can do with Amazon CloudWatch

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Metric stream, 6 operations

POSTdelete_metric_stream
Delete a CloudWatch metric stream.
POSTget_metric_stream
Retrieve detailed information about a specific CloudWatch metric stream.
POSTlist_metric_streams
List all CloudWatch metric streams in the account.
POSTput_metric_stream
Create or update a metric stream that sends CloudWatch metrics to Kinesis Data Firehose for real-time export.
POSTstart_metric_streams
Start one or more CloudWatch metric streams that are in the stopped state.
POSTstop_metric_streams
Stop one or more CloudWatch metric streams. Metrics are no longer exported until streams are started again.

Dashboard, 4 operations

POSTdelete_dashboards
Delete one or more CloudWatch dashboards. This action is irreversible.
POSTget_dashboard
Retrieve the details of a CloudWatch dashboard including its body definition in JSON format.
POSTlist_dashboards
List CloudWatch dashboards in your account. Optionally filter by a name prefix to find specific dashboards.
POSTput_dashboard
Create or update a CloudWatch dashboard. The dashboard body is a JSON string defining the widgets and their layout.

Alarm, 3 operations

POSTdelete_alarms
Delete one or more CloudWatch alarms. Deleted alarms stop evaluating metrics and executing actions.
POSTdescribe_alarms
Retrieve information about CloudWatch alarms. Filter by alarm names, state, or action prefix to monitor the status of your configured alarms.
POSTdescribe_alarms_for_metric
Retrieve all alarms configured for a specific metric. Useful for checking what monitoring is in place for a given metric and namespace.

Anomaly detector, 3 operations

POSTdelete_anomaly_detector
Delete a CloudWatch anomaly detection model. Specify either a single metric or metric math anomaly detector.
POSTdescribe_anomaly_detectors
List CloudWatch anomaly detection models associated with your account. Anomaly detectors use machine learning to determine normal ranges for metric values.
POSTput_anomaly_detector
Create or update an anomaly detection model for a CloudWatch metric. The model uses machine learning to determine the expected range of metric values based on historical patterns.

Alarm action, 2 operations

POSTdisable_alarm_actions
Disable actions for one or more CloudWatch alarms. When disabled, alarm actions do not execute even when the alarm changes state.
POSTenable_alarm_actions
Enable actions for one or more CloudWatch alarms. When enabled, alarm actions execute when the alarm changes state.

Metric data, 2 operations

POSTget_metric_data
Retrieve CloudWatch metric values using Metrics Insights queries or metric math expressions. Supports retrieving data for multiple metrics in a single request.
POSTput_metric_data
Publish metric data points to CloudWatch. You can publish data for new or existing metrics. Data is aggregated by CloudWatch based on the specified namespace and dimensions.

Resource, 2 operations

POSTtag_resource
Assign one or more tags to a CloudWatch resource (alarm or Contributor Insights rule). Tags are key-value pairs for organizing and managing resources.
POSTuntag_resource
Remove one or more tags from a CloudWatch resource (alarm or Contributor Insights rule). Specify the tag keys to remove from the resource.

Alarm history, 1 operation

POSTdescribe_alarm_history
Retrieve the history of a specific alarm or all alarms. Returns state transitions, configuration updates, and actions taken. Useful for auditing alarm behavior over time.

Alarm state, 1 operation

POSTset_alarm_state
Temporarily set the state of a CloudWatch alarm. Useful for testing alarm actions or temporarily suppressing alarms during maintenance.

Composite alarm, 1 operation

POSTput_composite_alarm
Create or update a composite CloudWatch alarm whose state is determined by a rule expression evaluating the states of other alarms.

Metric, 1 operation

POSTlist_metrics
List available CloudWatch metrics. Filter by namespace, metric name, or dimensions to discover what metrics are being collected for your AWS resources.

Metric alarm, 1 operation

POSTput_metric_alarm
Create or update a CloudWatch alarm. When the metric breaches the configured threshold, CloudWatch triggers the specified alarm actions such as SNS notifications or Auto Scaling policies.

Metric statistic, 1 operation

POSTget_metric_statistics
Get statistics for a specific CloudWatch metric. Returns aggregated data points based on the specified period, statistics, and time range.

Metric widget image, 1 operation

POSTget_metric_widget_image
Retrieve a snapshot of a CloudWatch metric graph as a base64-encoded PNG image.

Tag, 1 operation

POSTlist_tags_for_resource
List the tags associated with a CloudWatch resource. Returns all key-value tag pairs for the specified resource ARN.

Use Amazon CloudWatch from Claude Code, Cursor or Codex

Connect Amazon CloudWatch in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Amazon CloudWatch operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Amazon CloudWatch

Create your workspace
Sign up free. Nothing to install.
Connect Amazon CloudWatch once
Add your Amazon CloudWatch connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Amazon CloudWatch integration FAQ

What can you do with the Amazon CloudWatch integration?: LiveContext exposes 30 operations on Amazon CloudWatch, covering metric stream, dashboard, alarm and anomaly detector. Common uses include automate dashboard management, automate alarm management and describe alarm programmatically.