AWS Cost Analysis MCP server

The Cost Analysis MCP Server provides estimated AWS service costs before deployment, offering detailed cost breakdowns, natural language cost queries, and comprehensive cost reports to support informed infrastructure planning decisions.

Installation Prerequisites

Before installing the MCP server, you need to complete these prerequisites:

1. Install uv from Astral or GitHub
2. Install Python using uv:

   uv python install 3.10
   

3. Set up AWS credentials:
   • Create or use an existing AWS account with appropriate permissions
   • Configure credentials with aws configure or using environment variables
   • Ensure your IAM role/user has permissions to access the AWS Pricing API

Installation Options

Using UVX

Configure the MCP server in your MCP configuration file:

{
  "mcpServers": {
    "awslabs.cost-analysis-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.cost-analysis-mcp-server@latest"],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR",
        "AWS_PROFILE": "your-aws-profile"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Using Docker

First, build the Docker image:

docker build -t awslabs/cost-analysis-mcp-server .

Create an environment file with your AWS credentials:

AWS_ACCESS_KEY_ID=ASIAIOSFODNN7EXAMPLE
AWS_SECRET_ACCESS_KEY=wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
AWS_SESSION_TOKEN=AQoEXAMPLEH4aoAH0gNCAPy...truncated...zrkuWJOgQs8IZZaIv2BXIa2R4Olgk

Then configure your MCP configuration file:

{
  "mcpServers": {
    "awslabs.cost-analysis-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "--interactive",
        "--env",
        "FASTMCP_LOG_LEVEL=ERROR",
        "--env-file",
        "/full/path/to/file/above/.env",
        "awslabs/cost-analysis-mcp-server:latest"
      ],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}

Note: When using Docker, you'll need to keep your AWS credentials refreshed on your host machine.

AWS Authentication

The MCP server authenticates with AWS using the profile specified in the AWS_PROFILE environment variable:

"env": {
  "AWS_PROFILE": "your-aws-profile"
}

If no profile is specified, the server defaults to using the "default" AWS profile.

Your AWS credentials remain on your local machine and are used exclusively for accessing AWS services. Ensure your profile has the necessary permissions to access the AWS Pricing API.

Usage Features

Cost Analysis and Visualization

• Get detailed breakdowns of AWS costs by service, region, and tier
• Understand cost distribution across different services
• Generate pre-deployment cost estimates for infrastructure planning
• Analyze both CDK and Terraform projects to identify AWS services

Natural Language Cost Queries

• Ask questions about AWS costs using plain English
• Get instant answers from AWS pricing data without complex query languages
• Access pricing information before actual deployment

Cost Reports and Optimization

• Generate comprehensive cost estimates based on your infrastructure as code
• Receive cost optimization recommendations
• Support informed decision-making with upfront pricing analysis

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.