Amazon CloudWatch Logs MCP Server

What is Amazon CloudWatch Logs MCP Server?

A Model Context Protocol (MCP) server that provides tools for interacting with Amazon CloudWatch Logs services. It enables AI assistants to manage CloudWatch logs through a standardized interface using the AWS SDK.

How to use Amazon CloudWatch Logs MCP Server?

Install globally via npm (npm install -g @hyorimitsu/amazon-cloudwatch-logs-mcp-server) or pull the Docker image (ghcr.io/hyorimitsu/mcp-amazon-cloudwatch-logs:latest). Then add the server to your AI assistant’s configuration, setting the required environment variables AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY, and optionally AWS_REGION and READONLY.

Key features of Amazon CloudWatch Logs MCP Server

• Tools for log group, stream, and event operations
• Read-only mode for safe log viewing
• CloudWatch Logs Insights query support
• Deployable via npm or Docker
• Integrates with AI assistants through MCP

Use cases of Amazon CloudWatch Logs MCP Server

• AI assistant creates and manages log groups and streams
• Query and filter log events by time range or pattern
• Run CloudWatch Logs Insights queries for log analysis
• Enable read-only access to prevent accidental modifications

FAQ from Amazon CloudWatch Logs MCP Server

What does this MCP server do?

It provides a set of tools for AI assistants to interact with Amazon CloudWatch Logs, including creating, describing, and deleting log groups and streams, putting and retrieving log events, and running CloudWatch Logs Insights queries.

What are the prerequisites?

You need an AWS account with CloudWatch Logs access, an AWS access key and secret key with appropriate permissions, and either Node.js (for npm) or Docker installed.

Is this server ready for production use?

No. The project is actively under development and not yet ready for production. Features and APIs may change before the first stable release.

How do I enable read-only mode?

Set the READONLY environment variable to "true" in the server configuration. This disables all write operations (create, modify, delete) while keeping read operations available.

Can I run it with Docker?

Yes. Pull the image from ghcr.io/hyorimitsu/mcp-amazon-cloudwatch-logs:latest and configure your AI assistant to run it as a Docker container with the required AWS environment variables.