I Built an MCP Server That Gives AI Agents Real-Time AWS Pricing Data

Published: (December 19, 2025 at 10:44 PM EST)
2 min read
Source: Dev.to

Source: Dev.to

Cover image for I Built an MCP Server That Gives AI Agents Real-Time AWS Pricing Data

The Problem

You’re building an AI agent that provisions cloud infrastructure.
User says: “Spin up a t3.medium in the cheapest region.”

The agent has no idea what that costs, which region is cheapest, or whether reserved instances would save money. This makes it impossible to answer the most basic question: “How much will this cost?”

The Solution: AWS Pricing MCP

I built an MCP‑compatible API that returns real‑time AWS pricing data. It’s live on RapidAPI.

What it does

  • Query pricing for 20 AWS services (EC2, RDS, Lambda, S3, DynamoDB, ECS, EKS, etc.)
  • Compare prices across all 18 AWS regions
  • Provide on‑demand vs reserved instance breakdowns
  • Estimate monthly costs for multi‑instance workloads

How It Works

The API follows MCP (Model Context Protocol) conventions, so any MCP‑compatible AI client can use it directly.

Basic Query

curl -X GET "https://aws-pricing-mcp.p.rapidapi.com/ec2/pricing?instance_type=t3.medium&region=us-east-1" \
  -H "X-RapidAPI-Key: YOUR_KEY"

Response

{
  "instance_type": "t3.medium",
  "region": "us-east-1",
  "prices": {
    "on_demand_hourly": 0.0416,
    "on_demand_monthly": 30.37,
    "reserved_1yr_no_upfront_monthly": 24.82,
    "reserved_1yr_all_upfront_monthly": 21.90,
    "reserved_3yr_all_upfront_monthly": 14.60
  },
  "vcpu": 2,
  "memory_gb": 4,
  "potential_savings": {
    "reserved_1yr_percent": 27.9,
    "reserved_3yr_percent": 51.9
  }
}

Region Comparison

Find the cheapest region for any instance type:

curl -X GET "https://aws-pricing-mcp.p.rapidapi.com/ec2/compare-regions?instance_type=m5.xlarge"

Response

{
  "instance_type": "m5.xlarge",
  "cheapest_region": "us-east-2",
  "cheapest_price_monthly": 140.16,
  "most_expensive_region": "ap-northeast-1",
  "most_expensive_price_monthly": 185.04,
  "potential_savings_percent": 24.2,
  "all_regions": [
    {"region": "us-east-2", "monthly": 140.16},
    {"region": "us-east-1", "monthly": 142.08}
    // …
  ]
}

Multi‑Service Cost Estimation

Estimate costs for a complete workload:

curl -X POST "https://aws-pricing-mcp.p.rapidapi.com/estimate" \
  -H "Content-Type: application/json" \
  -d '{
    "region": "us-west-2",
    "resources": [
      {"service": "ec2", "instance_type": "t3.medium", "count": 3},
      {"service": "rds", "instance_type": "db.t3.medium", "count": 1},
      {"service": "s3", "storage_gb": 100}
    ]
  }'

Integration with AI Agents

If you’re building with Claude, GPT, or any MCP‑compatible system, the API responses are structured for easy parsing—no wrestling with AWS’s pricing API directly.

Example user prompt:
“What’s the cheapest way to run a 3‑node web tier with a managed database in AWS?”

Your agent can now answer with real numbers.

Services Supported

ServicePricing Data
EC2On‑demand, Reserved (1 yr/3 yr), Spot
RDSAll engines, Multi‑AZ
LambdaRequest + duration
S3Storage classes, transfer
DynamoDBOn‑demand + provisioned
ECS/EKSFargate + EC2 launch types
ElastiCacheRedis + Memcached
OpenSearchInstance + storage
20 services total

Pricing

TierRequests/MonthPrice
Free100$0
Pro5,000$49
Ultra25,000$149
Mega100,000$299

The free tier is enough to prototype and test.

Why I Built This

  1. AWS’s pricing API is painful. It requires complex filter queries and returns data in a format optimized for AWS, not developers.
  2. AI agents need structured data. Clean JSON with predictable schemas is essential—no XML, HTML scraping, or “check the console” workarounds.

Try It

The API is live on RapidAPI:

👉 AWS Pricing MCP on RapidAPI

Free tier available. No credit card required to start.

Back to Blog

Related posts

Read more »