Cloudwatch Logs MCP

🚀 CloudWatch Logs MCP Server

An MCP (Model Context Protocol) server that provides tools to access AWS CloudWatch logs. This server allows AI assistants to list CloudWatch log groups and read log entries from AWS CloudWatch.

🚀 Quick Start

This MCP server offers tools to interact with AWS CloudWatch logs, enabling AI assistants to perform operations such as listing log groups and retrieving log entries.

✨ Features

Available Tools

list_groups

List available CloudWatch log groups.

Parameters:

• prefix (optional): Log group name prefix
• region (optional): AWS region
• accessKeyId (optional): AWS access key ID
• secretAccessKey (optional): AWS secret access key
• sessionToken (optional): AWS session token

Return Value: A JSON string containing logGroupName, creationTime, and storedBytes.

get_logs

Get CloudWatch logs from a specific log group.

Parameters:

• logGroupName (required): Log group name
• logStreamName (optional): Log stream name
• startTime (optional): ISO format time or relative time (e.g., "5m", "1h", "1d")
• endTime (optional): ISO format end time
• filterPattern (optional): Log filter pattern
• region (optional): AWS region
• accessKeyId (optional): AWS access key ID
• secretAccessKey (optional): AWS secret access key
• sessionToken (optional): AWS session token

Return Value: A JSON string containing timestamp, message, and logStreamName.

📦 Installation

AWS Credentials

Ensure that AWS credentials are configured. You can configure them using the AWS CLI or by setting environment variables:

• AWS_ACCESS_KEY_ID
• AWS_SECRET_ACCESS_KEY

Usage with Claude Desktop

Add the following content to your claude_desktop_config.json file:

{
  "mcpServers": {
    "cloudwatch-logs": {
      "command": "python3",
      "args": ["/path/to/cloudwatch-logs-mcp/main.py"],
      "env": {
        "AWS_ACCESS_KEY_ID": "<YOUR_ACCESS_KEY_ID>",
        "AWS_SECRET_ACCESS_KEY": "<YOUR_SECRET_ACCESS_KEY>"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Docker

If you prefer to run the server in a Docker container, you can set up a Dockerfile and use the following configuration:

{
  "mcpServers": {
    "cloudwatch-logs": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "AWS_ACCESS_KEY_ID",
        "-e",
        "AWS_SECRET_ACCESS_KEY",
        "mcp/cloudwatch-logs"
      ],
      "env": {
        "AWS_ACCESS_KEY_ID": "<YOUR_ACCESS_KEY_ID>",
        "AWS_SECRET_ACCESS_KEY": "<YOUR_SECRET_ACCESS_KEY>"
      }
    }
  }
}

🔧 Technical Details

This server is built using the FastMCP class from the MCP SDK, which provides a simple way to create an MCP server. The server mainly exposes two tools:

1. list_groups: List available CloudWatch log groups.
2. get_logs: Read log entries from a specific log group.

Each tool is implemented as an asynchronous function decorated with @mcp.tool(). The server uses the boto3 library to interact with AWS services.

📄 License

This project is licensed under the MIT License.