# Replace your Azure DevOps with Claude

*   [Introduction](#introduction)
    
*   [Setup: Learn MCP Server](#setup-learn-mcp-server)
    
*   [Setup: Developer MCP Server](#setup-developer-mcp-server)
    
*   [Behind the Scene](#behind-the-scene)
    
*   [Reduce Hallucinations](#reduce-hallucinations)
    
*   [Claude for Observability](#claude-for-observability)
    
*   [Claude as Azure Well-Architected Expert](#claude-as-azure-well-architected-expert)
    
*   [How expensive is this setup?](#how-expensive-is-this-setup)
    
*   [How secure is this setup?](#how-secure-is-this-setup)
    
*   [Monitoring your AI](#monitoring-your-ai)
    
*   [The Downsides](#the-downsides)
    
*   [What about GCP and AWS?](#what-about-gcp-and-aws)
    
*   [Conclusion](#conclusion)
    

### Introduction

Claude and cloud goes together like peanut butter and jelly. As of July 2026, the easiest way to use Claude for DevOps work on Azure is the two official Microsoft Azure MCP servers. Microsoft separates its MCP Server into two implementations: the [Azure Learn MCP Server](https://learn.microsoft.com/en-us/training/support/mcp) for documentation and [Azure Developer MCP Server](https://learn.microsoft.com/en-us/azure/developer/azure-mcp-server/) for transactions.

Once you complete this setup, Claude will be your Azure subject matter expert on [Azure Well-Architected](https://learn.microsoft.com/en-us/azure/well-architected/) best practices.

### Setup: Learn MCP Server

1.  **Add Azure MCP plugin**  
    Start `claude` and enter the commands below to install the Azure Learn MCP server plugin
    

```plaintext
/plugin marketplace add microsoftdocs/mcp
/plugin install microsoft-docs@microsoft-docs-marketplace
```

![](https://cdn.hashnode.com/uploads/covers/69c85d2b7cf270651076d644/dd527c31-7d5d-4473-b907-c7813a724e7e.png align="center")

2.  **Connect the plugin**  
    Type the command below to start using the Azure Learn MCP server in Claude
    

```plaintext
/reload-plugins
```

The Learn MCP server is free to the public and does not require authentication.

Alternatively, if you choose to manually configure the Claude JSON configuration file, below is the `mcpServers` block.

```json
{
  "mcpServers": {
    "microsoft-learn": {
      "type": "http",
      "url": "https://learn.microsoft.com/api/mcp"
    }
  }
}
```

### Setup: Developer MCP Server

1.  **Create Entra Accounts for AI**  
    For infrastructure safety, do not use your regular Azure login for your AI agents. Create separate read-only and read-write [Azure Entra IDs](https://learn.microsoft.com/en-us/entra/fundamentals/what-is-entra) for each of your subscriptions. For this example, I created 2 IDs: `ai-readonly` and `ai-readwrite`.
    
    For the read-only ID, I assign it the [Reader](https://learn.microsoft.com/en-us/azure/role-based-access-control/built-in-roles/general#reader) built-in Azure role. For the read-write ID, I assign it the [Owner](https://learn.microsoft.com/en-us/azure/role-based-access-control/built-in-roles/privileged#owner) role because for any realistic scenario, Claude will need to create and assign IAM. To prevent accidental infrastructure deletions, you can [lock your resources](https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/lock-resources?tabs=json) or use [Azure denyAction policies](https://learn.microsoft.com/en-us/azure/governance/policy/concepts/effect-deny-action).
    
2.  **Install npx**  
    [npx](https://docs.npmjs.com/cli/v11/commands/npx) is the Node.js Package Executor. It runs Node.js packages without installing it locally. The best way to i[nstall npx](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm#using-a-node-version-manager-to-install-nodejs-and-npm) is via [nvm](https://github.com/nvm-sh/nvm) (Node.js Version Manager)
    
    ```shell
    curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.5/install.sh | bash
    source ~/.zshrc
    nvm install 24
    npx --version
    ```
    
3.  **Configure Claude to use the Azure Developer MCP Server**  
    Run the command below to add the Azure Developer MCP Server to Claude AI.
    
    ```shell
    claude mcp add azure-mcp --scope user -- npx -y @azure/mcp@2.0.3 server start
    ```
    
    Confirm the Azure MCP was successfully added
    
    ```shell
    claude mcp list
    ```
    
4.  **Sign into the Azure CLI**  
    The Azure Developer MCP Server uses the local [Azure CLI (`az`)](https://learn.microsoft.com/en-us/cli/azure/install-azure-cli?view=azure-cli-latest), the [Azure Developer CLI](https://learn.microsoft.com/en-us/azure/developer/azure-developer-cli/install-azd?tabs=winget-windows%2Cbrew-mac%2Cscript-linux&pivots=os-windows) (`azd`), and the Azure Core Tools (`func`) to access and modify your Azure resources. Install or upgrade these CLI tools as needed.
    
    Sign in via `az login` to the correct Azure subscription with the proper Entra ID created on step one.
    

### Behind the Scene

The Azure Model Context Protocol (MCP) Server acts as a translator between Claude and Azure. The Learn MCP Server searches the latest Microsoft Learn documentation for the most current answers. The Developer MCP Server configures the Azure CLI commands and executes it locally from your computer.

The Learn MCP server requires no authentication while the Developer MCP server uses the local `az login` Entra account.

### Reduce Hallucinations

Claude's knowledge ends on the training date cutoff of the AI model. For example, [Sonnet 4.6](https://www.anthropic.com/transparency) training date cutoff was May 2025. If you ask Sonnet 4.6 about Azure HorizonDB\](https://azure.microsoft.com/en-us/products/horizondb), it will think it is a fake product since it was first previewed in November 2025.

![](https://cdn.hashnode.com/uploads/covers/69c85d2b7cf270651076d644/86fa252f-99c7-4832-bb31-35f46766b10c.png align="center")

If you use the Azure Learn MCP server, Claude will use the most current Azure documentation and give you the correct answer about HorizonDB. (I do appreciate the little apology Claude gave me for the first wrong answer).

![](https://cdn.hashnode.com/uploads/covers/69c85d2b7cf270651076d644/3a8f9f43-0def-43af-8653-cdb1d5bf30a9.png align="center")

### Claude for Observability

Claude can use your read-only Azure credentials to analyze your Azure infrastructure. As a simple example, I asked Claude to list all my storage accounts buckets. As other examples, you can ask Claude:

*   *"Search Application Insights for errors from the Azure Function my-message-broker"*
    
*   *"Find all VMs using more than 90% CPU"*
    

![](https://cdn.hashnode.com/uploads/covers/69c85d2b7cf270651076d644/37884c7e-3cc1-4303-b617-fe9cb7662f01.png align="center")

### Claude as Azure Well-Architected Expert

Microsoft published an official set of [AI Skills for Azure](https://github.com/MicrosoftDocs/Agent-Skills). The Azure MCP Servers automatically load these skills without you having to do any additional complicated setup.

Using Claude and the [azure-functions skill,](https://github.com/MicrosoftDocs/Agent-Skills/blob/main/skills/azure-functions/SKILL.md) I was able to create and deploy an Azure Function coded with Node.js with full Azure Bicep infrastructure-as-code in about 8 minutes. If I did this by hand before AI, it would have taken me much longer than 8 minutes with equivalent results.

![](https://cdn.hashnode.com/uploads/covers/69c85d2b7cf270651076d644/947c9c3a-ed55-40b1-8c17-191a5bd7ca78.png align="center")

### How expensive is this setup?

Good news, it's free (mostly).

The Azure MCP servers are free to use. Of course, you still pay for Claude token usage and any Azure resources created. You can estimate Azure cost via the official [pricing calculator](https://azure.microsoft.com/en-us/pricing/calculator/).

### How secure is this setup?

This setup passed rigorous review by the Microsoft security team. In summary, the communication is end-to-end encrypted and uses your Entra ID permission setup. In addition, no information is permanently stored on Microsoft servers.

### Monitoring your AI

Commands executed by the Azure MCP servers on your Azure subscription are auditable in Activity Monitor.

![](https://cdn.hashnode.com/uploads/covers/69c85d2b7cf270651076d644/ffba0096-bdd5-4347-bef6-7ed4439a8924.png align="center")

### The Downsides

*   As an official Microsoft service, this AI setup uses `azd` and Azure Bicep as the infrastructure-as-code language. Like 97% of the DevOps community, you most likely use Terraform/OpenTofu. Additional steps are required to convert the answer into Terraform HCL
    
*   You may not like the answers if you disagree with the Azure Well-Architected framework.
    
*   Claude and most AI systems still offer questionable advice about Day 2 infrastructure operations such as upgrades and maintenance of existing resources. It will sometimes advise to delete infrastructure like databases instead of attempting to modify it.
    

### What about GCP and AWS?

Check out our [DevOps AI](https://devops-blog.com/series/devops-ai) section for information how to set up MCP servers for GCP and AWS.

### Conclusion

By powering up Claude with the Azure MCP Servers, it feels like having an Azure DevOps expert sit next to you and offer knowledgeable answers. On top of that, Claude can do the mundane task of creating, deploying, and monitoring Azure infrastructure. This frees you to concentrate on the important stuff, like creative ideas and business strategies.
