Azure
Summary
Microsoft's official Azure MCP server — manage cloud resources and query monitoring data conversationally.
Features
- Manage storage, databases, and Key Vault resources
- Query Azure Monitor logs with KQL
- Uses your existing Azure CLI credentials
Installation
Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.
Description
Microsoft's official Azure MCP server connects an assistant to an Azure subscription across a broad set of services.
Coverage
- Storage — blob containers, tables, and file shares
- Databases — Cosmos DB, Azure SQL, PostgreSQL, and MySQL
- Key Vault for secrets, keys, and certificates
- Azure Monitor with KQL queries against Log Analytics workspaces, which is the killer feature: writing correct KQL from memory is genuinely hard
- AI services including Azure OpenAI and AI Search
- Resource management — subscriptions, resource groups, and configuration
- Azure CLI and Developer CLI invocation for anything not covered by a dedicated tool
Authentication
It uses DefaultAzureCredential, meaning it inherits whatever identity you are already signed in with through the Azure CLI. No separate credential handling, and the assistant's permissions are exactly your permissions — which is worth thinking about if you are signed in as an owner.
Runs with npx -y @azure/mcp@latest server start. Actively developed by Microsoft.
Related MCP Servers
DigitalOcean
by DigitalOcean
DigitalOcean's official MCP server — deploy apps and manage Droplets, databases, and storage conversationally.
Heroku
by Heroku
Heroku's official MCP server — manage apps, dynos, add-ons, config, and logs from an AI client.
AWS Labs MCP
by AWS Labs
AWS Labs' core MCP server — the entry point to AWS's official collection of service-specific MCP servers.

Kubernetes MCP Server
by containers (Red Hat)
Native Go MCP server for Kubernetes and OpenShift — talks to the API server directly, no kubectl required.