Infrawise
Azure FinOps infrastructure cost optimization
README
@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.
Quickstart
npx @infrawise/mcp-server@latest setup
That'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 list
Switching 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 auth
Local development
npm install
npm run build
node dist/index.js setup # or auth / doctor
Environment variables
| Variable | Default | Purpose |
|---|---|---|
INFRAWISE_API_BASE |
https://api.infrawiseai.com/api |
Backend base URL |
INFRAWISE_AZURE_CLIENT_ID |
9d7c8230-3c1d-4a81-80cb-98f5cb40d2e7 |
Public client app the CLI signs in as |
INFRAWISE_AZURE_API_SCOPE |
api://06dc6d06-11f1-4543-bb2c-9c91b263df56/delegated_access |
Token scope (the Infrawise API audience) |
INFRAWISE_AZURE_AUTHORITY |
https://login.microsoftonline.com/common |
MSAL authority |
INFRAWISE_AZURE_TENANT_ID |
(unset) | Optional tenant override; builds authority URL automatically |
Security
- Token cache stored at
~/.infrawise/mcp-credentials.json - Written with
0600mode (best effort on Windows) - Read-only server — all calls are GET only
Releases
Releases are managed by the Infrawise team and published to npm as @infrawise/mcp-server.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.