opencloudcosts 1.0.2

MCP server for cloud pricing (AWS, GCP, Azure)

OpenCloudCosts MCP

Anchor AI FinOps to real, live cloud pricing.

An open source MCP server that gives AI assistants accurate cloud pricing data for AWS, GCP, and Azure.

Supports both public list pricing (no credentials needed for AWS and Azure; GCP requires a free API key) and effective (custom Private Pricing Agreement) rates (post-discount: Reserved Instances, Savings Plans, CUDs, EDPs).

Key Use Cases

• "What is the on-demand price of an m5.xlarge in us-east-1 vs ap-southeast-2, and what's the % delta?"
• "Give me a TCO estimate for this architecture: 3x m5.xlarge + 1x 500GB gp3 EBS in us-east-1"
• "What's the cost per user if I run this stack for 50,000 MAUs?"
• "List all c6g instances in eu-west-1 with >= 8 vCPUs"
• "What's my effective hourly rate on m5.xlarge after Savings Plans?"

Tools (v1.0.0 — 16 tools)

Pricing

Tool	Description
get_price	Unified pricing dispatcher — compute, storage, database, AI, networking, serverless, analytics, observability
get_prices_batch	Prices for multiple instance types in one call (concurrent)
compare_prices	Compare a spec across multiple regions with optional baseline deltas
search_pricing	Free-text search across the pricing catalog

Discovery

Tool	Description
describe_catalog	Full support matrix or targeted field guidance + copy-paste example_invocation for get_price
list_regions	All regions with friendly names
list_instance_types	Available instance types with vCPU/memory filters

Region Analysis

Tool	Description
find_cheapest_region	Cheapest region for any service spec, concurrently
find_available_regions	Every region where a service is available, sorted by price
get_spot_history	AWS spot price history and stability analysis (requires credentials)

FinOps

Tool	Description
get_discount_summary	Account-wide RI / Savings Plan / CUD utilisation (requires credentials)
estimate_bom	TCO for a multi-resource Bill of Materials
estimate_unit_economics	Cost per user/request/transaction

Cache

Tool	Description
refresh_cache	Invalidate pricing cache
cache_stats	Cache entry counts and DB size

See docs/tools.md for full parameter reference and docs/finops-guide.md for usage examples.

Setup

Option 1 — pip (easiest, cross-platform)

The PyPI package wraps the native Go binary — no Go toolchain needed.

pip install opencloudcosts
opencloudcosts            # stdio mode (for local MCP clients)
opencloudcosts --transport http --host 0.0.0.0 --port 8080  # HTTP mode

Option 2 — binary download

Download the pre-built binary for your platform from the latest release:

# Linux (amd64)
curl -L https://github.com/x7even/cloudcostsmcp/releases/latest/download/opencloudcosts_linux_amd64.tar.gz | tar xz
./opencloudcosts

# macOS (Apple Silicon)
curl -L https://github.com/x7even/cloudcostsmcp/releases/latest/download/opencloudcosts_darwin_arm64.tar.gz | tar xz
./opencloudcosts

Option 3 — Docker / container

# Build the image first (no pre-built image is published)
cd opencloudcosts-go
docker build -t opencloudcosts:local .

# Run — HTTP transport, bound to all interfaces
docker run -p 8080:8080 \
  -e OCC_GCP_API_KEY=AIza... \
  -v ~/.aws:/root/.aws:ro \
  opencloudcosts:local

The image is ~15 MB (distroless scratch base, static binary). No credentials are required for AWS and Azure public pricing.

Option 4 — build from source

git clone https://github.com/x7even/cloudcostsmcp
cd cloudcostsmcp/opencloudcosts-go
CGO_ENABLED=0 go build -o opencloudcosts ./cmd/opencloudcosts
./opencloudcosts

Connect to Claude Code

Stdio (local process — recommended for single-user)

Add to ~/.claude/settings.json or your project's .mcp.json:

{
  "mcpServers": {
    "cloudcost": {
      "command": "opencloudcosts",
      "env": {
        "OCC_GCP_API_KEY": "AIza..."
      }
    }
  }
}

HTTP (shared/remote server — one server, many clients)

{
  "mcpServers": {
    "cloudcost": {
      "transport": "http",
      "url": "http://localhost:8080/"
    }
  }
}

Kubernetes

See deploy/kubernetes/ for manifests. Build and push your own image (see Docker section above), then reference it in deployment.yaml. Credentials are passed via environment variables or Kubernetes Secrets — same variable names as the Docker examples above.

Test with MCP Inspector

npx @modelcontextprotocol/inspector opencloudcosts

AWS Credentials

Feature	Credentials needed
Public pricing (EC2, EBS, RDS list prices)	None
Effective pricing (RI / SP discounts)	AWS credentials + OCC_AWS_ENABLE_COST_EXPLORER=true

Minimal IAM policy for public pricing:

{
  "Effect": "Allow",
  "Action": ["pricing:GetProducts", "pricing:DescribeServices", "pricing:GetAttributeValues"],
  "Resource": "*"
}

Add these for effective pricing:

"ce:GetCostAndUsage", "savingsplans:DescribeSavingsPlans", "savingsplans:DescribeSavingsPlanRates"

Configuration

All settings via environment variables (prefix OCC_) or .env file:

Variable	Default	Description
OCC_CACHE_TTL_HOURS	24	Public price cache TTL
OCC_AWS_ENABLE_COST_EXPLORER	false	Enable AWS effective pricing (costs $0.01/call)
OCC_DEFAULT_REGIONS	us-east-1,us-west-2	Default regions
AWS_PROFILE	(default chain)	AWS credentials profile
OCC_GCP_BILLING_ACCOUNT_ID	(none)	GCP billing account ID for contract/effective pricing

Caching

Prices are cached in SQLite at ~/.cache/opencloudcosts/pricing.db. Public list prices are cached for 24 hours — AWS pricing changes infrequently. Use the refresh_cache tool to force a refresh.

GCP Setup

Unlike AWS (which has public bulk pricing endpoints), GCP's pricing API always requires at least a free API key. No credit card or billing account is needed.

Option A — Free API key (recommended, 2 min setup):

1. Go to console.cloud.google.com/apis/credentials
2. Create a Project if you don't have one (free)
3. Click Create Credentials → API key
4. Set the key:

export OCC_GCP_API_KEY=AIza...

Or add OCC_GCP_API_KEY=AIza... to your .env file.

Option B — Application Default Credentials (if you already use gcloud):

gcloud auth application-default login
# or set GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json

GCP instance type format: {family}-{series}-{vcpus} e.g. n2-standard-4, e2-highmem-8, c2-standard-16

GCP Contract / Effective Pricing

If you have a negotiated pricing contract with Google Cloud, you can retrieve your actual discounted rates (EDP, custom pricing) via the Cloud Billing Pricing API v1beta. This requires:

1. ADC credentials: gcloud auth application-default login
2. billing.billingAccountPrice.get IAM permission on your billing account
3. Your billing account ID:

export OCC_GCP_BILLING_ACCOUNT_ID=012345-567890-ABCDEF

With this configured, get_price responses for GCP compute will include an effective_price block showing your contract rate and discount percentage. Without it, public list prices are returned unchanged.

Azure Setup

Azure pricing is fully public — no credentials, API key, or subscription needed.

# No configuration needed — works out of the box
uv run opencloudcosts

Azure instance type format: ARM SKU names e.g. Standard_D4s_v3, Standard_E8s_v3, Standard_B2ms

Azure pricing terms: on_demand (default), reserved_1yr, reserved_3yr, spot

Azure regions: ARM region names e.g. eastus, westeurope, southeastasia (use list_regions for full list)

Azure supported services:

Domain	Service	Description
compute	vm	Virtual Machines — all families, Linux/Windows, on-demand/spot/reserved
storage	managed_disks	Premium SSD, Standard SSD, Standard HDD, Ultra Disk
storage	blob	Blob Storage
database	sql	Azure SQL Database, Azure DB for MySQL/PostgreSQL — vCore tiers, HA, reserved
database	cosmos	Cosmos DB — provisioned (per 100 RU/s), serverless, autoscale
container	aks	AKS cluster management fee (free tier or $0.10/hr Standard)
serverless	azure_functions	Functions Consumption plan — per GB-second + per execution
ai	openai	Azure OpenAI — GPT-4o, GPT-4, GPT-3.5-Turbo, o1, embeddings
inter_region_egress	—	Outbound data transfer — internet and inter-region, Zone 1 rates, 5 GB/month free

GCP pricing terms: on_demand (default), spot (preemptible), cud_1yr, cud_3yr

Security

OpenCloudCosts can access sensitive billing data when configured with cloud credentials (AWS Cost Explorer, GCP billing, Azure contract pricing). Follow these guidelines to keep that data safe.

Credential hygiene

• Use dedicated, least-privilege credentials — read-only access scoped to pricing and billing APIs only. Never use root, owner, or admin credentials.
• AWS: create an IAM user/role with only ce:GetCostAndUsage, pricing:GetProducts, and savingsplans:Describe* permissions.
• Store credentials in .env (see .env.example) and never commit that file to version control.

Transport security

• The default stdio transport is safe — the server runs as a local process with no network exposure.
• If you use --transport http, never expose it publicly without a reverse proxy and authentication in front of it. Treat it as an internal service.

MCP client trust

• Only add this server to MCP client configs you control.
• Avoid running it alongside untrusted third-party MCP servers — a malicious server can craft prompts that cause the LLM to call your billing tools and relay the results.

What this server can access With credentials configured: actual spend, contract/negotiated pricing, reservation and savings plan data. Understand this before granting access in shared or multi-user environments.

Recent releases

• v0.9.1 ✅ GCP egress contract pricing; fix PricingResult.source Literal
• v0.9.2 ✅ Azure OpenAI model matching fix; Azure Functions pricing fix; list_instance_types cap; AWS bulk pricing via ijson; 199-prompt harness suite
• v1.0.0 ✅ Go rewrite — static binary, dual stdio/HTTP transport, 16 tools, compare_bom cross-cloud workload comparison, concurrent region fan-out (32 goroutines), Azure o1-mini SKU fix; 234/234 (100%) LLM grounding harness
• v1.0.1 ✅ PyPI package description; CI Trusted Publisher fix; go install tag