MCPgee
MCPgee
MCPgeeMCPgee

Azure Kubernetes Service

v1.0.0•Cloud Services•stable

A Model Context Protocol (MCP) server that enables AI assistants to interact with AKS clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and AKS.

kubernetesmcp-servermodel-context-protocol
Share:
132
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Azure Kubernetes Service?

Azure Kubernetes Service is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server that enables ai assistants to interact with aks clusters. it serves as a bridge between ai tools (like claude, cursor, and github copilot) and aks.

A Model Context Protocol (MCP) server that enables AI assistants to interact with AKS clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and AKS.

This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A Model Context Protocol (MCP) server that enables AI assist

Use Cases

Interact with AKS clusters
Manage Azure Kubernetes resources
Enable AI interaction with cloud infrastructure
Azure

Maintainer

LicenseMIT
Languagego
Versionv1.0.0
UpdatedMay 18, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx aks

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Azure Kubernetes Service

The AKS MCP Server is an open-source bridge that lets AI assistants like Claude, Cursor, and GitHub Copilot interact directly with Azure Kubernetes Service clusters. It exposes unified tools such as `call_az`, `call_kubectl`, and `aks_monitoring` so you can manage clusters, inspect networking, run diagnostics, and query observability data through natural language. The server supports three access levels (readonly, readwrite, admin) and can run locally, in VS Code, or deployed in-cluster via Helm with workload identity. Teams use it to accelerate AKS operations, troubleshoot incidents, and automate fleet management without leaving their AI coding assistant.

Prerequisites

  • Azure CLI installed and authenticated via `az login`
  • An Azure subscription with one or more AKS clusters
  • Go 1.24+ if building from source (pre-built binaries available for all platforms)
  • An MCP-compatible client such as Claude Desktop, VS Code with the AKS extension, or Cursor
  • Appropriate Azure RBAC permissions on the target subscription or resource group
1

Download the AKS MCP binary

Download the pre-built binary for your platform from the GitHub Releases page at https://github.com/Azure/aks-mcp/releases. Place it somewhere on your PATH, for example /usr/local/bin/aks-mcp on macOS/Linux.

# macOS example (replace version and arch as needed)
curl -L https://github.com/Azure/aks-mcp/releases/latest/download/aks-mcp-darwin-amd64 -o /usr/local/bin/aks-mcp
chmod +x /usr/local/bin/aks-mcp
2

Authenticate with Azure

Log in with the Azure CLI so the server can acquire tokens for your subscription. For unattended environments use a service principal or workload identity via environment variables.

az login
# Optionally set a default subscription
az account set --subscription "<YOUR_SUBSCRIPTION_ID>"
3

Configure environment variables for service principal auth (optional)

If you prefer non-interactive authentication, set these environment variables before starting the server. For local development, `az login` is sufficient and no variables are needed.

export AZURE_TENANT_ID="<tenant-id>"
export AZURE_CLIENT_ID="<client-id>"
export AZURE_CLIENT_SECRET="<client-secret>"
export AZURE_SUBSCRIPTION_ID="<subscription-id>"
4

Add the server to your MCP client configuration

Edit your Claude Desktop or VS Code MCP config file to register the AKS MCP server. Choose an access level appropriate for your use case: readonly for safe exploration, readwrite for cluster management, admin for full control.

{
  "mcpServers": {
    "aks": {
      "command": "/usr/local/bin/aks-mcp",
      "args": ["--access-level", "readonly", "--transport", "stdio"]
    }
  }
}
5

Verify the connection

Restart your MCP client and ask it to list your AKS clusters. If the server is running correctly you should receive a JSON list of clusters from your subscription.

Azure Kubernetes Service Examples

Client configuration

Claude Desktop configuration for the AKS MCP server with read-write access level and stdio transport.

{
  "mcpServers": {
    "aks": {
      "command": "/usr/local/bin/aks-mcp",
      "args": [
        "--access-level", "readwrite",
        "--transport", "stdio",
        "--log-level", "info"
      ],
      "env": {
        "AZURE_SUBSCRIPTION_ID": "<your-subscription-id>"
      }
    }
  }
}

Prompts to try

Natural language prompts you can send to your AI assistant after connecting the AKS MCP server.

- "List all my AKS clusters in my Azure subscription"
- "What is the node pool configuration and current node count for cluster prod-aks?"
- "Show me the networking setup (VNet, subnets, NSGs) for my AKS cluster"
- "Get the last 50 lines of kubelet logs from node aks-nodepool1-12345"
- "Run an AKS advisor scan and show me cost optimization recommendations"
- "Scale the user node pool in prod-aks to 5 nodes"

Troubleshooting Azure Kubernetes Service

Server exits immediately with 'az: command not found' or authentication errors

Ensure the Azure CLI is installed and `az login` has been run in the same shell environment. If using a service principal, verify that AZURE_TENANT_ID, AZURE_CLIENT_ID, and AZURE_CLIENT_SECRET are all set correctly before starting the MCP server.

kubectl operations fail with 'no kubeconfig found' or 'cluster not reachable'

The server uses `az aks get-credentials` internally. Ensure your Azure identity has the 'Azure Kubernetes Service Cluster User Role' on the target cluster, and that the cluster API server is reachable from your machine (check firewall/private endpoint settings).

Mutations are rejected even though they should be allowed

Check the --access-level flag in your config. With `readonly`, create/delete/apply operations are blocked by design. Change to `--access-level readwrite` or `admin` to enable write operations.

Frequently Asked Questions about Azure Kubernetes Service

What is Azure Kubernetes Service?

Azure Kubernetes Service is a Model Context Protocol (MCP) server that model context protocol (mcp) server that enables ai assistants to interact with aks clusters. it serves as a bridge between ai tools (like claude, cursor, and github copilot) and aks. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Azure Kubernetes Service?

Follow the installation instructions on the Azure Kubernetes Service GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Azure Kubernetes Service?

Azure Kubernetes Service works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Azure Kubernetes Service free to use?

Yes, Azure Kubernetes Service is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Azure Kubernetes Service Alternatives — Similar Cloud Services Servers

Looking for alternatives to Azure Kubernetes Service? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.

Open WebUI

★ 138.2k

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Anything LLM

★ 60.4k

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

LocalAI

★ 46.4k

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Nacos

★ 33.0k

an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

Xiaozhi ESP32

★ 26.7k

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

Gateway

★ 11.8k

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Browse More Cloud Services MCP Servers

Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Cloud ServicesBrowse All Servers

Quick Config Preview

{ "mcpServers": { "aks": { "command": "npx", "args": ["-y", "aks"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Azure Kubernetes Service?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides