generated: '2026-06-20'
method: searched
status: published
source: https://awslabs.github.io/mcp/servers/cloudwatch-mcp-server
description: >-
  Official AWS Labs CloudWatch MCP server. Runs locally (stdio) on the same host
  as the LLM client and uses the caller's AWS credentials to expose CloudWatch
  metrics, PromQL, alarms, and Logs Insights for AI-assisted troubleshooting.
  Announced July 2025 alongside the Application Signals MCP server.
server:
  name: awslabs.cloudwatch-mcp-server
  transport: stdio
  hosting: local
  repo: https://github.com/awslabs/mcp/tree/main/src/cloudwatch-mcp-server
  package:
    registry: pypi
    name: awslabs.cloudwatch-mcp-server
    url: https://pypi.org/project/awslabs.cloudwatch-mcp-server/
    install: uvx awslabs.cloudwatch-mcp-server@latest
tools:
  - name: get_metric_data
    description: Retrieve detailed metric data with percentiles, math expressions, and multi-metric batching.
  - name: get_metric_metadata
    description: Obtain comprehensive metadata about a specific CloudWatch metric.
  - name: get_recommended_metric_alarms
    description: Suggest alarm configurations based on best practices and statistical analysis.
  - name: analyze_metric
    description: Examine metric data for trends, seasonality, and statistical properties.
  - name: execute_promql_query
    description: Run an instant PromQL query returning single-point-in-time values.
  - name: execute_promql_range_query
    description: Execute a PromQL query over a time window for trend analysis.
  - name: get_promql_label_values
    description: Retrieve values for a specific PromQL label for metric discovery.
  - name: get_promql_series
    description: Find time series matching PromQL label selectors.
  - name: get_promql_labels
    description: List available PromQL label names.
  - name: get_active_alarms
    description: Identify currently active alarms across the account.
  - name: get_alarm_history
    description: Retrieve historical state changes and patterns for alarms.
  - name: describe_log_groups
    description: Find metadata about log groups.
  - name: analyze_log_group
    description: Analyze logs for anomalies, patterns, and errors.
  - name: execute_log_insights_query
    description: Execute a Logs Insights query on log groups.
  - name: execute_cwl_insights_batch
    description: Run queries across multiple log groups/regions with automatic handling.
  - name: get_logs_insight_query_results
    description: Retrieve results from an executed Logs Insights query.
  - name: cancel_logs_insight_query
    description: Cancel an in-progress Logs Insights query.
related_servers:
  - name: awslabs.cloudwatch-appsignals-mcp-server
    description: Companion Application Signals MCP server for SLO and service-map troubleshooting.
    url: https://awslabs.github.io/mcp/servers/cloudwatch-appsignals-mcp-server