MCP server
Azure MCP server
Microsoft's Azure MCP server lets AI work with many Azure services, from storage and Key Vault to SQL, monitoring and AKS, with a read-only mode.
- Official server
- Cloud and infrastructure
At a glance
- Maintained by
- Microsoft
- Tools exposed
- 10 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
For companies on Microsoft's cloud, Azure hosts apps, databases and data. Microsoft's Azure MCP server groups its tools by service: resource groups, subscriptions, storage, Key Vault, Cosmos DB, SQL, monitoring, App Service, Kubernetes and pricing, among others.
An assistant can answer questions about resources, read monitoring data and, if allowed, make changes, all through your Azure identity.
Starting it in read-only mode blocks writes, which we recommend by default. Tools that return secrets ask for confirmation. Use an identity with a narrow role assignment rather than a subscription owner.
Use cases
Best business use cases
Resource questions
Monitoring
Pricing
Data services
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
In the default namespace mode each Azure service is one tool named after its namespace (names above are from Microsoft Learn's tools table). In 'all' mode tools have long names such as azmcp_storage_account_get.
Read and write: Read and write across many Azure services. Start with --read-only to block writes. Secret-returning tools ask for user confirmation.
-
groupList resource groups and the resources in a group.
-
subscriptionList Azure subscriptions.
-
storageManage storage accounts, containers, blobs and tables.
-
keyvaultList and create keys, secrets and certificates.
-
cosmosWork with Cosmos DB accounts, databases, containers and items.
-
sqlWork with Azure SQL servers, databases and firewall rules.
-
monitorQuery Azure Monitor logs and metrics.
-
appserviceManage App Service web apps, settings and deployments.
-
aksList Azure Kubernetes Service clusters.
-
pricingGet Azure retail prices and cost estimates.
Workflows
Example workflows
Investigate an app slowdown
-
1
Connect in read-only mode.
-
2
Ask about the App Service app.
-
3
The assistant reads monitoring data.
-
4
It points to the likely cause.
-
5
An engineer fixes it.
Estimate a new setup
-
1
Describe the resources needed.
-
2
The assistant checks pricing.
-
3
It builds a monthly estimate.
-
4
It notes cheaper options.
-
5
The team decides.
Prompts
Example prompts
“List all resources in the production resource group.”
“Show errors for the API app in the last hour.”
“Estimate the monthly cost of two more App Service instances.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"azure-mcp-server": {
"command": "npx",
"args": [
"-y",
"@azure/mcp@latest",
"server",
"start"
]
}
}
}Claude Code: terminal
claude mcp add azure-mcp-server -- npx -y @azure/mcp@latest server start- Local server: npm: @azure/mcp (stdio, run as `npx -y @azure/mcp@latest server start`). Also .mcpb bundles for Claude Desktop..
- Needs: Azure credentials: az login (Azure CLI), managed identity, or AZURE_TENANT_ID / AZURE_CLIENT_ID / AZURE_CLIENT_SECRET. Azure RBAC limits access..
Security
Security considerations
-
Read-only first
Start with read access and add actions only for reviewed tasks.
-
Scoped credentials
Use a dedicated role or token with the least access, never an owner or admin key.
-
Separate environments
Keep production changes out of assistant sessions, or require approval for them.
-
Audit
Use Azure activity logs to review actions.
Related servers
Servers that pair well with it
AWS
The AWS API MCP server from AWS Labs lets AI run AWS CLI commands, suggest commands and plan changes, with read-only and consent modes.
Google Cloud
Google's gcloud MCP servers let AI run gcloud commands, read logs, metrics, alerts and traces, and work with Cloud Storage.
Microsoft Teams
Microsoft's Teams MCP server, part of its Work IQ preview, lets AI list and read chats and channels and post messages and replies.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- Product scaling Keep a growing product fast and stable as users, data and features increase.
- Multi-tenant architecture One product serving many customer accounts, with each account's data kept separate and secure.
- Dashboards and reporting Dashboards that pull numbers from the systems you already use and show what matters without a spreadsheet.
- API integration Make two systems share data reliably, with retries, logging and alerts when something goes wrong.
- AI-Powered Web Development Business websites, customer portals, dashboards and web applications that load fast, rank well and are easy to change.
Solutions
View all solutions- Automated reporting Reports that build themselves from your systems on schedule, with a plain-language summary of what changed.
- Compliance tracking Track filing deadlines, licenses and obligations in one place, with reminders and AI summaries of relevant rule changes.
- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
Industries
View all industriesCase studies
View all case studiesGuides and articles
View all guides and articles- How to connect AI to your database safely Let staff ask questions of your data in plain English without risking production systems or sensitive records.
- How to set up automated reporting Replace manual weekly and monthly reports with dashboards and summaries that update themselves.
- How we review AI-generated code The checks we apply to every AI-assisted change, from tests and security to readability and business rules.
- MCP security best practices How to choose, configure and monitor MCP servers so AI assistants get the access they need and nothing more.
- How to automate reporting with AI and MCP Build reports that assemble themselves from your systems through MCP, with a written summary people can trust.
- PostgreSQL vs MySQL The two most popular open-source databases compared for business applications.
Glossary terms
View all glossary terms- API integration An API integration connects two or more systems through their APIs so data and actions flow between them automatically.
- Database A database is an organized store of data that software can search, update and keep consistent, such as customers, orders or bookings.
- Cloud hosting Cloud hosting runs websites and applications on servers rented from a provider, which can grow or shrink with demand.
- Reverse proxy A reverse proxy is a server that sits in front of your applications, receiving visitors' requests and passing them to the right app, often adding security and caching.
- VPS A VPS, or virtual private server, is a rented virtual machine with its own resources, on which you can install and run your own software.
- API An API, or application programming interface, is a defined way for one piece of software to request data or actions from another.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. It is maintained by Microsoft.
Yes. Start it with the read-only option.
In its default mode, tools are grouped by Azure service.