Installation¶

This guide covers how to install and set up AWS Logs MCP for both one-click installation in VS Code and manual installation.

Installation Options¶

Choose your preferred AI assistant and installation method:

VSCode¶

One-click installation¶

Direct terminal command¶

# With AWS profile (recommended)
AWS_PROFILE=your-profile-name npx -y aws-logs-mcp --stdio

VS Code extension MCP configuration¶

{
  "name": "aws-logs",
  "displayName": "AWS Logs MCP",
  "command": "npx",
  "args": ["-y", "aws-logs-mcp", "--stdio"],
  "env": {
    "AWS_PROFILE": "default",
    "AWS_REGION": "us-east-1"
  }
}

Claude Code¶

# Install the aws-logs MCP tool in Claude Code
claude mcp add aws-logs -s user -- npx -y aws-logs-mcp --stdio

GitHub Copilot and other MCP-compatible assistants¶

# Run with stdio mode (recommended for AI assistants)
npx aws-logs-mcp --stdio

Claude Desktop¶

For Claude Desktop, follow the MCP Quickstart for Users and add AWS Logs MCP as a custom tool.

{
  "name": "aws-logs",
  "displayName": "AWS Logs MCP",
  "command": "npx",
  "args": ["-y", "aws-logs-mcp", "--stdio"],
  "env": {
    "AWS_PROFILE": "default",
    "AWS_REGION": "us-east-1"
  }
}

Manual Installation¶

If you need more control or want to customize your installation, you can choose one of the manual installation methods below. These methods provide the same functionality as the one-click installation but allow for more advanced configuration options.

The one-click installation above takes care of the AWS authentication automatically based on your input. For manual installation, you'll configure these options in your .env file as described in the Configuration guide.

Prerequisites for Manual Installation¶

If you prefer to install manually, ensure you have the following installed:

Node.js 18+ and pnpm
AWS credentials with appropriate permissions
Docker (optional, for containerization)

Direct Usage¶

Clone the repository:¶

git clone https://github.com/schuettc/aws-logs-mcp.git
cd aws-logs-mcp

Install dependencies:¶

pnpm install

Set up environment variables:¶

cp .env.example .env

Edit the .env file with your AWS credentials.

Build and start the server:¶

For HTTP mode (default):

pnpm build
pnpm start

For STDIO mode (recommended for AI assistants):

pnpm build
pnpm start:stdio

For development with hot-reloading:

# HTTP mode
pnpm dev

# STDIO mode
pnpm dev:stdio

Docker Usage¶

Build and run using Dockerfile¶

For HTTP mode:

docker build -t aws-logs-mcp .
docker run -p 3000:3000 --env-file .env aws-logs-mcp

For STDIO mode (for AI assistants):

docker build -t aws-logs-mcp .
docker run -i --env-file .env aws-logs-mcp --stdio

Build and run using Docker compose¶

For HTTP mode:

docker-compose up -d --build

For STDIO mode (for AI assistants):

docker-compose run -T --build aws-logs-mcp --stdio