Cloud Cost MCP

Multi-cloud pricing comparison MCP server for AWS, Azure, GCP, and OCI. Compare compute, storage, egress, and Kubernetes costs across all major cloud providers with a single query.

⚠️ DISCLAIMER: All pricing data is retrieved from publicly available APIs and data sources including instances.vantage.sh, Azure Retail Prices API, and Oracle Cloud Price List API. This data is provided for informational and estimation purposes only. Cloud pricing changes frequently and may vary by region, account type, commitment terms, and other factors. Users are solely responsible for verifying all pricing information directly with cloud providers before making any purchasing or architectural decisions. The authors make no warranties about the accuracy, completeness, or timeliness of this data.

Features

• Comprehensive Coverage: 4,900+ instance types across all providers

  • AWS: 1,300+ EC2 instances + 1,180+ managed-database types + Lightsail

  • Azure: 1,680+ VM types (official Azure Retail Prices API)

  • GCP: 360+ instance types across 40+ regions

  • OCI: 600+ products via Oracle API

• No API Keys Required: All data from public APIs (instances.vantage.sh + provider APIs)

• Fresh data, two ways: AWS/Azure/GCP bundled data is auto-refreshed weekly via GitHub Actions, and the refresh_* tools fetch live pricing on demand (cached 60 min in-memory). OCI bundled data is curated. See Data freshness for the exact model.

• Natural Language Queries: Ask Claude "What's cheapest for 4 vCPU 16GB?"

• Workload Calculator: Estimate full workload costs including compute, storage, and egress

• Migration Planning: Calculate potential savings when switching providers

Related MCP server: Cost Management MCP

Installation

For Claude Code Users

# One-command install
claude mcp add cloud-cost -- npx -y cloud-cost-mcp

For Claude Desktop Users

Add this to your claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json), then restart Claude Desktop:

{
  "mcpServers": {
    "cloud-cost": {
      "command": "npx",
      "args": ["-y", "cloud-cost-mcp"]
    }
  }
}

Manual Installation

npm install -g cloud-cost-mcp

Then reference the installed binary in any MCP client config:

{
  "mcpServers": {
    "cloud-cost": {
      "command": "cloud-cost-mcp"
    }
  }
}

Usage Examples

Once installed, just ask Claude:

Compare Compute

"Compare 4 vCPU 16GB VMs across AWS, Azure, GCP, and OCI"
"Find the cheapest cloud for an 8-core VM with 32GB RAM"
"What's the best deal for ARM instances with 4 cores?"

Compare Storage

"Compare object storage pricing for 1TB across all clouds"
"What's the cheapest archival storage for 10TB?"

Compare Egress (OCI Advantage!)

"Compare egress costs for 5TB monthly"
"What's the cheapest cloud for 10TB data transfer?"

Note: OCI offers 10TB/month free egress - 100x more than AWS/Azure/GCP!

Full Workload Estimates

"Estimate cost for 3 VMs with 4 vCPU each, 500GB storage, and 1TB egress"
"What would a Kubernetes cluster with 5 nodes cost across all clouds?"

Quick Estimates

"Quick estimate for a medium API server"
"Compare all clouds for a kubernetes-cluster preset"
"Estimate cost for gpu-training-large preset"

GPU Pricing (OCI)

"List all available GPU shapes"
"Compare A100 vs H100 GPU pricing"
"What GPU should I use for ML training with 80GB memory?"
"Get details for BM.GPU.H100.8"

Migration Planning

"How much could I save migrating from AWS to OCI?"
"Compare my current GCP setup against other clouds"

Available Tools

Comparison Tools

Calculator Tools

Available presets: small-web-app, medium-api-server, large-database, ml-training, kubernetes-cluster, data-lake, high-egress-cdn, high-traffic-web, gpu-inference, gpu-training-small, gpu-training-large

Data Management Tools

Real-Time API Tools

AWS (1,147 EC2 + 353 RDS + Lightsail)

GCP (287 instance types)

Azure (1,199 VM types)

OCI (600+ products)

GPU Tools (OCI)

Available GPU shapes: A10, A100 80GB, H100 80GB, H200 141GB, L40S, MI300X

Status

Data Freshness

All providers now support real-time pricing refresh via public APIs:

Use check_api_status to verify API accessibility. Use get_data_freshness to check bundled data age.

Key Insights

OCI Cost Advantages

• 10TB/month free egress (vs 100GB on AWS/Azure/GCP)

• Free Kubernetes control plane (basic clusters)

• Uniform global pricing (no regional variation)

• Always Free tier includes 4 OCPUs + 24GB RAM on ARM

Free Kubernetes Control Planes

• OCI (OKE): Free basic clusters

• Azure (AKS): Free control plane

• AWS (EKS) and GCP (GKE): $73/month per cluster

Example Output

User: "Compare cost for a 4 vCPU, 16GB RAM VM across all clouds"

┌─────────┬──────────────────────┬────────┬──────────┬─────────────┐
│ Provider│ Instance Type        │ vCPUs  │ Memory   │ Monthly Cost│
├─────────┼──────────────────────┼────────┼──────────┼─────────────┤
│ OCI     │ VM.Standard.E5.Flex  │ 4      │ 16 GB    │ $61.32      │
│ GCP     │ e2-standard-4        │ 4      │ 16 GB    │ $97.82      │
│ AWS     │ t3.xlarge            │ 4      │ 16 GB    │ $121.47     │
│ Azure   │ Standard_D4s_v5      │ 4      │ 16 GB    │ $140.16     │
└─────────┴──────────────────────┴────────┴──────────┴─────────────┘

Cheapest: OCI ($61.32/month) - 50% savings vs AWS

Development

# Clone and install
git clone https://github.com/jasonwilbur/cloud-cost-mcp.git
cd cloud-cost-mcp
npm install

# Build
npm run build

# Test locally with Claude Code
claude mcp add cloud-cost-dev -- node /path/to/cloud-cost-mcp/dist/index.js

Data freshness

This server uses a two-tier data model — it helps to know which is which:

1. Bundled data (src/data/bundled/*.json) is what the comparison/calculator tools read by default, so the server works instantly with no network calls.

   • AWS, Azure, GCP bundled data is regenerated from live upstream sources (instances.vantage.sh + the official Azure Retail Prices API) and auto-refreshed weekly via the refresh-data GitHub Action. You can also regenerate locally with npm run fetch-data.

   • OCI bundled data is curated (vantage.sh has no OCI feed) and updated manually. For always-live OCI pricing, use the refresh_oci_pricing tool or the dedicated oci-pricing-mcp.

2. Live refresh tools (refresh_aws_ec2_pricing, refresh_azure_full_pricing, refresh_gcp_pricing, refresh_oci_pricing, refresh_aws_rds_pricing) fetch current pricing from provider APIs at call time, cached 60 minutes in-memory for the life of the process. These return fresh data to the caller but do not rewrite the bundled files — that only happens via npm run fetch-data / the weekly Action.

Use get_data_freshness to see the bundled timestamp and staleness for each provider.

License

Apache-2.0

Author

Jason Wilbur (jasonwilbur.com)

Related Projects

• oci-pricing-mcp - Dedicated OCI pricing MCP with 25+ tools