awslabs.cloudwatch-mcp-server
An AWS Labs Model Context Protocol (MCP) server for cloudwatch
Decision gist · record as of 2026-08-14
Yes—if you are building an AI agent or LLM-based troubleshooting system that needs to query CloudWatch. The package is actively maintained, has no known vulnerabilities, low install friction, and a permissive license. Prerequisites are AWS credentials and Python 3.10+; the server must run on the same host as your LLM client. Not suitable for standalone CLI use or non-agent workflows.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires AWS credentials configured (via aws configure or environment variables) and an AWS account with CloudWatch permissions.
- Must run on the same host as the LLM client.
- Low friction: pure Python wheel with no compiled dependencies.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most projects.
last release 2026-08-10 (4 days) · last repo commit 2026-08-14 · 9,598 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 195,680 downloads/mo, #9,808 on PyPI
Alternatives
Verify before relying
pip install awslabs.cloudwatch-mcp-server
from mcp.server import Server
import boto3
# Initialize and configure the MCP server with CloudWatch client
# Server exposes tools like get_active_alarms(), analyze_log_group(), execute_promql_query()- Specific AWS IAM permissions required beyond 'CloudWatch access' for all tool operations
- Performance characteristics when querying large log groups or metric ranges
- Whether PromQL enrichment requires additional setup beyond the documented `aws cloudwatch start-otel-enrichment` command
What it is and what it does
This is an MCP server that bridges AI agents and LLMs to CloudWatch observability data. It wraps CloudWatch APIs into task-oriented tools—alarm troubleshooting, log anomaly detection, metric analysis, and PromQL queries—so agents can diagnose and resolve AWS service issues without custom integrations. The server runs locally alongside your LLM client and requires AWS credentials to access your account's CloudWatch telemetry.
The package depends on boto3 for AWS API calls, pydantic for data validation, and statistical libraries (numpy, statsmodels, pandas) to analyze trends, seasonality, and anomalies in metrics and logs. It also uses loguru for logging and the mcp library to implement the protocol itself. The tool set includes alarm history analysis, log pattern detection, metric metadata retrieval, and both instant and range PromQL queries—designed to support incident response workflows where agents need to correlate metrics, logs, and alarm state to recommend remediation.
Use it for
- Automated root cause analysis: agent queries active alarms, retrieves related metrics and logs, analyzes patterns to identify the underlying issue.
- Anomaly detection in logs: agent scans CloudWatch log groups for error patterns and message anomalies within a time window to surface operational problems.
- Metric trend analysis: agent retrieves metric data with percentile statistics and math expressions to understand performance trends and seasonality.
- Cross-region log search: agent runs Logs Insights queries across multiple log groups and regions in a single batch call with automatic chunking and throttling.
- Alarm configuration recommendations: agent analyzes a metric's statistical properties and suggests alarm thresholds and evaluation periods.
- PromQL-based metric discovery: agent queries OTLP-ingested and enriched AWS metrics using PromQL label selectors to find relevant time series.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes—if you are building an AI agent or LLM-based troubleshooting system that needs to query CloudWatch.
The package is actively maintained, has no known vulnerabilities, low install friction, and a permissive license. Prerequisites are AWS credentials and Python 3.10+; the server must run on the same host as your LLM client. Not suitable for standalone CLI use or non-agent workflows.
Install
awslabs-cloudwatch-mcp-server on PyPI
Before you install
Low friction: pure Python wheel with no compiled dependencies. Active maintenance—released 4 days ago with 9598 repository stars. Requires Python 3.10 or later and AWS credentials configured locally.
Requires AWS credentials configured (via aws configure or environment variables) and an AWS account with CloudWatch permissions. Must run on the same host as the LLM client.
License in practice
Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most projects.
Quickstart
pip install awslabs.cloudwatch-mcp-server
from mcp.server import Server
import boto3
# Initialize and configure the MCP server with CloudWatch client
# Server exposes tools like get_active_alarms(), analyze_log_group(), execute_promql_query()Verify before relying
- Specific AWS IAM permissions required beyond 'CloudWatch access' for all tool operations
- Performance characteristics when querying large log groups or metric ranges
- Whether PromQL enrichment requires additional setup beyond the documented `aws cloudwatch start-otel-enrichment` command
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 8 packagesboto3logurumcpnumpypandaspydanticrequestsstatsmodels |
| Maintenance | Actively maintained 4 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 195,680 / month, #9,808 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: awslabs_cloudwatch_mcp_server-0.1.8-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “cloudwatch mcp server”
- awslabs.cloudwatch-mcp-serverExposes CloudWatch metrics, logs, alarms, and PromQL queries through…
- mcp-grafanaAn MCP server that exposes Grafana dashboards, datasources, and query…
- mcp-proxymcp-proxy bridges Model Context Protocol (MCP) servers and clients…
Give your agent the search over MCP, or paste the wish link into any chat.
More Monitoring packages
Wraps any iterable to display a real-time progress bar in the terminal or Jupyter notebook, showing iteration count, elapsed time, and estimated time remaining.
Provides generated Python code for OpenTelemetry semantic conventions, enabling standardized attribute naming and constant definitions for instrumentation and telemetry collection.
Install it if you are using OpenTelemetry and want to follow semantic conventions correctly.
Provides the reference implementation of the OpenTelemetry API for collecting and exporting traces, metrics, and logs from Python applications.
Provides the abstract API and interfaces for OpenTelemetry instrumentation in Python, defining how to emit traces, metrics, and logs without tying code to a specific SDK implementation.
Exports OpenTelemetry observability data to an OpenTelemetry Collector using Protobuf-encoded messages over HTTP.
Install it if you are using OpenTelemetry in Python and need to send data to a Collector over HTTP.
Provides automatic instrumentation commands and programmatic APIs to inject distributed tracing into Python applications without code changes, detecting and instrumenting packages used by your program.
Install it if you need distributed tracing without code changes and have compatible instrumented packages in your environment.
See also awslabs.eks-mcp-server · mcp-grafana · awslabs.aws-documentation-mcp-server · aws-embedded-metrics · awslabs.aws-api-mcp-server · awslabs.aws-pricing-mcp-server · awslogs · awslabs.billing-cost-management-mcp-server · awslabs.redshift-mcp-server · lambda-warmer-py