AWS Support: Getting started with the AWS Pricing MCP and Amazon Q CLI

In today's cloud landscape, developers and financial analysts increasingly rely on Amazon Q for cost estimation and optimization, leveraging its powerful ability to parse through pricing documentation and provide relevant solutions. However, when pricing scenarios require deeper analysis or access to real-time pricing data, the AWS Pricing API becomes essential. By combining Amazon Q with the Pricing MCP server, teams can streamline their cost analysis workflow significantly. This integration allows them to seamlessly access and analyze pricing information while maintaining the context of their conversation with the AI assistant, eliminating the need to manually search through complex pricing tables and calculators. The result is a more efficient, integrated pricing experience that bridges the gap between AI-assisted cost analysis and AWS's comprehensive pricing data. Here's how to get started:

Important Note: This server provides real-time pricing data from the AWS Pricing API. We cannot guarantee that AI assistants will always construct filters correctly or identify the absolute cheapest options. All calls are free of charge.

Prerequisites

• Install uv from Astral or the GitHub README
• Install Python using uv python install 3.10
• Set up AWS credentials with access to AWS services
• You need an AWS account with appropriate permissions
• Configure AWS credentials with aws configure or environment variables
• Ensure your IAM role/user has pricing:* permissions to access the AWS Pricing API

Configure the MCP server in your MCP client configuration (e.g., for Amazon Q Developer CLI, edit ~/.aws/amazonq/mcp.json): replacing your-aws-profile and your AWS region of choice

{
  "mcpServers": {
    "awslabs.aws-pricing-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.aws-pricing-mcp-server@latest"],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR",
        "AWS_PROFILE": "your-aws-profile",
        "AWS_REGION": "us-east-1"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Example Session

Start a chat with Amazon Q

q chat

and start to ask your question

I'd like to know how much it would cost to send 100TB of data from the eu-west-1 region to the us-east-1 region from an S3 bucket using standard storage to an S3 also using standard storage. I'd like to use datasync in enhanced mode as well.

Q will respond

I'll help you estimate the costs for transferring 100TB of data from an S3 bucket in eu-west-1 to another S3 bucket in us-east-1 using AWS DataSync in enhanced mode. Let me use the AWS pricing tools to get this information for you.

Based on the information I've gathered, here's the cost estimate for transferring 100TB of data from an S3 bucket in eu-west-1 to another S3 bucket in us-east-1 using AWS DataSync in enhanced mode:

Cost Estimate Summary

AWS DataSync Enhanced Mode Costs

• Data Transfer Rate: $0.015 per GB
• Task Execution Fee: $0.55 per task execution
• Total Data: 100TB = 102,400GB
• Calculation: ($0.015/GB × 102,400GB) + ($0.55 × 1 task) = $1,536.55

Total Estimated Cost: $1,536.55`

Key Details:

1. This estimate is based on ON DEMAND pricing for AWS DataSync in Enhanced mode.
2. The calculation includes both the per-GB data transfer fee and the task execution fee.
3. The estimate assumes a single DataSync task execution for the entire 100TB transfer.`

Important Notes:

• This estimate excludes S3 storage costs in both regions
• S3 request costs (PUT, GET, etc.) are not included
• Any additional DataSync task executions beyond the initial transfer would incur additional costs
• The estimate is based on current AWS pricing as of July 2025

If you need a more detailed breakdown or want to explore cost optimization options for this transfer, please let me know.

In this example we noticed the model suggested that this didn’t include the S3 storage costs so we asked it to include these as well

can you also include an estimate S3 request cost - the 100TB is made up of 2GB files only. I'd also like to know how much the S3 storage costs would contribute to the total

Based on the information I've gathered, I'll provide a comprehensive cost estimate for transferring 100TB of data (consisting of 2GB files) from an S3 bucket in eu-west-1 to another S3 bucket in us-east-1 using AWS DataSync in enhanced mode.

Complete Cost Estimate

1. AWS DataSync Enhanced Mode Costs

• Data Transfer Rate: $0.015 per GB

• Task Execution Fee: $0.55 per task execution

• Total Data: 100TB = 102,400GB

• Calculation: ($0.015/GB × 102,400GB) + ($0.55 × 1 task) = $1,536.55

2. S3 Request Costs

• Number of 2GB Files: 100TB ÷ 2GB = 51,200 files

• PUT Requests (destination): $0.005 per 1,000 requests

• 51,200 files ÷ 1,000 × $0.005 = $0.256

• GET Requests (source): $0.0004 per 1,000 requests

• 51,200 files ÷ 1,000 × $0.0004 = $0.02048

3. S3 Storage Costs (Monthly)

• S3 Standard Storage in eu-west-1: $0.023 per GB-month for first 50TB
• 50TB × 1,024 × $0.023 = $1,177.60
• Remaining 50TB × 1,024 × $0.022 = $1,126.40
• Total source storage: $2,304.00 per month
• S3 Standard Storage in us-east-1: Similar pricing structure (approximately $0.023 per GB-month)
• Total destination storage: ~$2,304.00 per month

Total One-Time Transfer Cost

• DataSync Enhanced Mode: $1,536.55
• S3 Request Costs: $0.28
• Total One-Time Cost: $1,536.83

Monthly Storage Costs (If Keeping Both Copies)

• Source bucket (eu-west-1): $2,304.00 per month
• Destination bucket (us-east-1): $2,304.00 per month
• Total Monthly Storage: $4,608.00 per month

Important Notes:

1. This estimate assumes a single DataSync task execution for the entire 100TB transfer.
2. The S3 storage costs are ongoing monthly costs as long as you keep the data in both regions.
3. The DataSync and request costs are one-time costs for the transfer operation.
4. Actual costs may vary slightly based on the exact pricing in each region and any potential volume discounts.
5. This estimate doesn't include any potential network costs within AWS (which are typically minimal for transfers between AWS regions using AWS services).
6. If you delete the source data after transfer, you would only incur the destination storage costs going forward.

References

https://github.com/awslabs/mcp/tree/main/src/aws-pricing-mcp-server