Skip to main content
Glama
vivek-daml

AWS Cost Estimator MCP

by vivek-daml

AWS Cost Estimator MCP

An end-to-end AWS cost estimation solution for teams. Ask your AI IDE to build an estimate — get a formatted Excel report with real pricing, INR conversion, and best practices. No manual steps.

What This Does

You say:  "Generate a cost report for Acme Corp with 3 EC2 m5.large and RDS PostgreSQL in ap-south-1"

AI does:  1. Builds estimate with full validation (Node.js MCP)
          2. Saves to calculator.aws → gets shareable URL
          3. Opens URL in headless browser → scrapes real costs
          4. Generates formatted Excel (.xlsx) with INR pricing

You get:  Acme_Corp_Cost_Report.xlsx in your project folder

Related MCP server: AWS FinOps MCP Server

Two MCP Servers Working Together

Server

Language

What it does

AWS Pricing Calculator MCP

Node.js

Searches 436+ AWS services, validates configs, builds estimates, exports to calculator.aws

Cost Report Generator MCP

Python

Takes the estimate URL, fetches real costs via headless browser, produces formatted Excel

Quick Start

See SETUP.md for complete step-by-step instructions.

TL;DR

# Clone
git clone https://github.com/vivek-daml/aws-cost-estimator-mcp.git
cd aws-cost-estimator-mcp

# Node.js side (estimate creation)
npm install
npm run build

# Python side (report generation)
cd cost-report-mcp
python -m venv .venv
.venv\Scripts\activate        # Windows
pip install -r requirements.txt
playwright install chromium
cd ..

Add to ~/.kiro/settings/mcp.json (or equivalent for Claude Desktop / Cursor / VS Code). Replace /path/to/aws-cost-estimator-mcp with the actual folder where you cloned this repo, and use forward slashes / (not backslashes) in the paths:

{
  "mcpServers": {
    "aws-pricing-calculator-mcp-server": {
      "command": "node",
      "args": ["/path/to/aws-cost-estimator-mcp/dist/mcp-server.js"],
      "disabled": false,
      "autoApprove": [
        "search_services",
        "get_service_fields",
        "create_estimate",
        "add_service",
        "validate_estimate",
        "export_estimate",
        "build_estimate"
      ]
    },
    "aws-cost-report-generator": {
      "command": "/path/to/aws-cost-estimator-mcp/cost-report-mcp/.venv/Scripts/python.exe",
      "args": ["/path/to/aws-cost-estimator-mcp/cost-report-mcp/server.py"],
      "disabled": false,
      "autoApprove": [
        "generate_cost_report_excel",
        "generate_cost_report_from_csv",
        "get_exchange_rate"
      ]
    }
  }
}

Excel Report Output

The generated report includes:

  • Summary sheet — total monthly cost in INR

  • AWS Services sheet — S.NO, Service, Per Month USD, Per Month INR, Per Year INR

  • EC2/RDS details — Instance Type, vCPU, RAM, OS/Database, Running Hours, Pricing Model

  • Pricing Link — the calculator.aws URL for reference

  • Notes — region, exchange rate, per-service configuration descriptions

  • Best Practices — 5 AI-generated recommendations (via AWS Bedrock Nova Pro)

Compatible AI Tools

Tool

Works?

Kiro

Yes

Claude Desktop

Yes

Cursor

Yes

VS Code + GitHub Copilot

Yes

Claude Code (CLI)

Yes

Windsurf

Yes

Amazon Q Developer

Yes

Architecture

┌──────────────┐                          ┌──────────────────────────────┐
│  AI Agent    │── MCP (estimate tools) ──│ Node.js Pricing Calculator   │
│  (Kiro etc.) │                          │ (validation, lint, catalog)  │
│              │                          └──────────────┬───────────────┘
│              │                                         │ saves to AWS
│              │                                         ▼
│              │                          ┌──────────────────────────────┐
│              │── MCP (report tool) ─────│ Python Report Generator      │
│              │                          │ (Playwright + Excel format)  │
└──────────────┘                          └──────────────────────────────┘

Requirements

  • Node.js 18+

  • Python 3.10+

  • Internet access (AWS CloudFront CDN — no credentials needed for estimates)

  • AWS credentials (optional — only for Bedrock-powered best practices)

License

MIT-0

Related MCP Connectors

Related MCP Servers

  • A
    license
    B
    quality
    D
    maintenance
    Provides a comprehensive suite of 76 tools for AWS cloud resource optimization, cost management, and infrastructure monitoring. It enables users to identify unused resources, analyze cost trends, right-size capacity, and maintain security compliance through natural language.
    76
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables natural language analysis of AWS costs, automated FinOps waste audits, and budget monitoring across multiple profiles and regions while keeping credentials secure locally.
    183
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables creating AWS cost estimates through natural language, generating shareable calculator.aws links, and retrieving actual calculated costs via headless Chrome, without requiring AWS credentials.
    101 npm
    7
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to parse multi-cloud infrastructure-as-code files, query real-time pricing from AWS, Azure, and GCP, and generate cost estimates and comparison reports.
    12 npm
    MIT