Amazon CloudWatch Logs MCP Server

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

Note: This project is currently under active development and not yet ready for production use. Features and APIs may change significantly before the first stable release.

Overview

This MCP server allows AI assistants to interact with Amazon CloudWatch Logs through the Model Context Protocol. It provides a standardized interface for performing various CloudWatch Logs operations, enabling comprehensive management and monitoring of log data.

Quick Start

Prerequisites

• AWS account with CloudWatch Logs access
• AWS access key and secret key with appropriate permissions
• Node.js (for npm installation) or Docker

Installation

Choose one of the following installation methods:

Option 1: npm Package

# Install the package
npm install -g @hyorimitsu/amazon-cloudwatch-logs-mcp-server

# Configure in your AI assistant's configuration
# See Configuration section below

Option 2: Docker Image

# Pull the Docker image
docker pull ghcr.io/hyorimitsu/mcp-amazon-cloudwatch-logs:latest

# Configure in your AI assistant's configuration
# See Configuration section below

Option 3: Local Development Build

# Clone the repository
git clone https://github.com/hyorimitsu/mcp-amazon-cloudwatch-logs.git
cd mcp-amazon-cloudwatch-logs

# Install dependencies
pnpm install

# Build the project
pnpm run build

# Configure in your AI assistant's configuration
# See Configuration section below

Configuration

Add the server to your AI assistant's configuration:

For npm Installation

{
  "mcpServers": {
    "amazon-cloudwatch-logs": {
      "command": "amazon-cloudwatch-logs-mcp-server",
      "env": {
        "AWS_REGION": "us-east-1",
        "AWS_ACCESS_KEY_ID": "<YOUR_ACCESS_KEY>",
        "AWS_SECRET_ACCESS_KEY": "<YOUR_SECRET_KEY>"
      }
    }
  }
}

For Docker Installation

{
  "mcpServers": {
    "amazon-cloudwatch-logs": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "AWS_REGION",
        "-e",
        "AWS_ACCESS_KEY_ID",
        "-e",
        "AWS_SECRET_ACCESS_KEY",
        "ghcr.io/hyorimitsu/mcp-amazon-cloudwatch-logs"
      ],
      "env": {
        "AWS_REGION": "us-east-1",
        "AWS_ACCESS_KEY_ID": "<YOUR_ACCESS_KEY>",
        "AWS_SECRET_ACCESS_KEY": "<YOUR_SECRET_KEY>"
      }
    }
  }
}

For Local Development Build

{
  "mcpServers": {
    "amazon-cloudwatch-logs": {
      "command": "node",
      "args": ["/path/to/mcp-amazon-cloudwatch-logs/build/index.js"],
      "env": {
        "AWS_REGION": "us-east-1",
        "AWS_ACCESS_KEY_ID": "<YOUR_ACCESS_KEY>",
        "AWS_SECRET_ACCESS_KEY": "<YOUR_SECRET_KEY>"
      }
    }
  }
}

Environment Variables

Read-Only Mode

Enable read-only mode by setting the READONLY environment variable to "true":

"env": {
  "AWS_REGION": "us-east-1",
  "AWS_ACCESS_KEY_ID": "<YOUR_ACCESS_KEY>",
  "AWS_SECRET_ACCESS_KEY": "<YOUR_SECRET_KEY>",
  "READONLY": "true"
}

In read-only mode:

• Only READ operations (tools that retrieve or query information) are available
• WRITE operations (tools that create, modify, or delete resources) are disabled

This is useful for scenarios where you want to allow log viewing but prevent any modifications to your CloudWatch Logs resources.

Available Tools

Log Group Operations

Log Stream Operations

Log Event Operations

For detailed documentation on each tool, including parameters and examples, see TOOLS.md.

Note: This project is under development. Additional CloudWatch Logs operations are planned for future releases.

Development

For information on developing and extending this project, please see CONTRIBUTING.md.

License

This project is licensed under the MIT License - see the LICENSE file for details.