AWS MCP server for AI agents

This MCP server enables AI assistants like Claude to interact with your AWS environment, allowing you to use natural language for querying and managing AWS resources during conversations. It acts as a better alternative to Amazon Q by connecting Claude directly to your AWS infrastructure.

Prerequisites

Node.js
Claude Desktop
AWS credentials configured locally (~/.aws/ directory)

Installation

Clone the repository:

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

Install dependencies:

pnpm install
# or
npm install

Configuration

Setting up Claude Desktop

Open Claude desktop app and navigate to Settings -> Developer -> Edit Config
Add the following entry to your claude_desktop_config.json:

{
  "mcpServers": {
    "aws": {
      "command": "npm", // OR pnpm
      "args": [
        "--silent",
        "--prefix",
        "/Users/<YOUR USERNAME>/aws-mcp",
        "start"
      ]
    }
  }
}

Important: Replace /Users/<YOUR USERNAME>/aws-mcp with the actual path to your project directory.

Restart the Claude desktop app. You should see a connection status indicator:

Using with `nvm`

If you're using Node Version Manager, you'll need to build from source first and add the following configuration:

{
  "mcpServers": {
    "aws": {
      "command": "/Users/<USERNAME>/.nvm/versions/node/v20.10.0/bin/node",
      "args": [
        "<WORKSPACE_PATH>/aws-mcp/node_modules/tsx/dist/cli.mjs",
        "<WORKSPACE_PATH>/aws-mcp/index.ts",
        "--prefix",
        "<WORKSPACE_PATH>/aws-mcp",
        "start"
      ]
    }
  }
}

Using the MCP Server

After configuration, you can interact with your AWS environment through Claude using natural language. Start by:

Selecting an AWS profile, or
Asking questions directly, such as:
- "List available AWS profiles"
- "List all EC2 instances in my account"
- "Show me S3 buckets with their sizes"
- "What Lambda functions are deployed in us-east-1?"
- "List all ECS clusters and their services"

Troubleshooting

If you encounter issues, check the server logs:

tail -n 50 -f ~/Library/Logs/Claude/mcp-server-aws.log
# or
tail -n 50 -f ~/Library/Logs/Claude/mcp.log

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

AWS MCP server