Infrawise
OfficialThe Infrawise MCP server provides Azure FinOps cost optimization tools, helping you identify and act on cost-saving opportunities across your Azure subscriptions.
get_idle_resources: Retrieve idle or zombie Azure resources that can be deleted or deallocated to reduce unnecessary costs.get_sku_optimizations: Get rightsizing recommendations for overprovisioned resources (e.g., downsizing SKUs).get_general_recommendations: Access strategic purchasing model and licensing optimizations (e.g., reserved instances, hybrid benefits).get_savings_summary: View an aggregated breakdown of total potential savings across all categories.
All tools accept an optional subscription_filter (UUID) to scope results to a specific Azure subscription, or return merged results across all accessible subscriptions when omitted.
@infrawise/mcp-server
Claude Code MCP server for Infrawise Azure FinOps recommendations.
What it provides
Tools exposed to Claude Code:
get_idle_resources— idle/zombie resources to delete or deallocateget_sku_optimizations— rightsizing recommendations for overprovisioned resourcesget_general_recommendations— purchasing model and licensing optimizationsget_savings_summary— aggregated savings totals across all categories
All tools accept an optional subscription_filter (subscription UUID) to scope results.
Related MCP server: kubopt
Quickstart
npx @infrawise/mcp-server@latest setupThat's it. setup opens your browser for Azure sign-in, registers the MCP server with Claude Code, and confirms everything is working. Restart Claude Code when it completes.
Prerequisite: You need an active Infrawise account with at least one Azure subscription onboarded. Complete onboarding →
Useful commands
# Re-authenticate only (e.g. after switching accounts) — opens browser
npx @infrawise/mcp-server@latest auth
# Pin a specific tenant
npx @infrawise/mcp-server@latest auth --tenant <tenantId>
# Diagnose auth and onboarding issues with fix steps
npx @infrawise/mcp-server@latest doctor
# Check that the MCP server is registered
claude mcp listSwitching accounts
Delete the cached credentials and re-authenticate:
# macOS / Linux
rm ~/.infrawise/mcp-credentials.json
# Windows (PowerShell)
Remove-Item "$env:USERPROFILE\.infrawise\mcp-credentials.json"
npx @infrawise/mcp-server@latest authLocal development
cd packages/claude-mcp
npm install
npm run build
node dist/index.js setup # or auth / doctorPublishing a new version
cd packages/claude-mcp
npm version patch # or minor / major
npm publish --access publicprepublishOnly runs clean && build automatically. Verify after publishing:
npm view @infrawise/mcp-server versionExisting users re-run npx @infrawise/mcp-server@latest setup to pick up the new version — no config clearing or MCP re-registration needed.
Environment variables
Variable | Default | Purpose |
|
| Backend base URL |
|
| Public client app the CLI signs in as |
|
| Token scope (the Infrawise API audience) |
|
| MSAL authority |
| (unset) | Optional tenant override; builds authority URL automatically |
Security
Token cache stored at
~/.infrawise/mcp-credentials.jsonWritten with
0600mode (best effort on Windows)Read-only server — all calls are GET only
Available Tools
4 toolsget_general_recommendationsC
Retrieve strategic purchasing and licensing optimization recommendations.
Inputs: subscription_filter.
get_idle_resourcesA
Retrieve idle and zombie Azure resources that can be deleted or deallocated for cost savings.
Inputs: subscription_filter.
get_savings_summaryA
Aggregate savings totals across idle resources, SKU rightsizing, and general recommendations.
Inputs: subscription_filter.
get_sku_optimizationsA
Retrieve rightsizing recommendations for overprovisioned resources.
Inputs: subscription_filter.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct aspect of cost optimization: general recommendations, idle resources, savings summary, and SKU optimizations. No overlap exists.
All tools follow a consistent 'get_<noun_phrase>' pattern, making them predictable and easy to distinguish.
With 4 tools covering the core categories of cost optimization (recommendations, idle resources, SKU, summary), the count is well-scoped for the domain.
The set covers retrieval of all major cost-saving categories, but lacks tools for taking actions (e.g., applying recommendations) or drilling into historical data, which are minor gaps.
Maintenance
Related MCP Connectors
Cloud cost + FinOps knowledge for AI agents: AWS/Azure/GCP optimisation, AI spend, waste playbooks.
Cloud, SaaS and AI spend in one system of record. Each saving applied for you or shipped as code.
- Costory FinOps MCPDeprecatedio.costory
FinOps harness MCP: allocated cloud, data and LLM bills. Build on it or switch. Cloud read-only.
Related MCP Servers
- AlicenseAqualityCmaintenanceCloud cost management MCP server for Azure. Ask your AI about your cloud bill.15104 npm1MIT
- AlicenseAqualityCmaintenanceKubernetes cluster cost analysis and optimization. Query costs, find savings opportunities, get rightsizing recommendations, and analyze pod spend across AKS, EKS, and GKE — directly from Claude612Apache 2.0
- AlicenseNot gradedqualityDmaintenanceProduction-grade MCP server for enterprise Azure cost optimization, enabling spend anomaly detection, multi-tenant auditing, budget validation, and compliance-aware recommendations.1MIT
- AlicenseNot gradedqualityDmaintenanceAnalyzes Azure cloud costs, audits for waste, and provides budget insights via natural language through a secure local MCP server.16 PyPI2MIT