# AKS-MCP — MCP Bridge for Azure Kubernetes

> Use AKS-MCP to bridge MCP-compatible assistants to Azure Kubernetes Service operations; run via Docker MCP Toolkit or build from source with `make`.

## Install

Merge the JSON below into your `.mcp.json`:

## Quick Use

```bash
git clone https://github.com/Azure/aks-mcp && cd aks-mcp
make build
# Configure your MCP client to run the built `aks-mcp` binary with: --transport stdio
```

## Intro

Use AKS-MCP to ask an assistant about AKS clusters and execute controlled cluster operations through an MCP server.

Use AKS-MCP to bridge MCP-compatible assistants to Azure Kubernetes Service operations; run via Docker MCP Toolkit or build from source with `make`.

**Best for:** platform teams operating AKS who want an MCP tool surface for cluster inventory, troubleshooting, and controlled changes

**Works with:** Go toolchain (for build), Azure credentials, kubeconfig paths, MCP clients using stdio transport

**Setup time:** ~15–30 minutes (auth + build/toolkit + first client config)

### Key facts (verified)

- GitHub: 132 stars · 37 forks · pushed 2026-05-12.
- License: MIT · owner avatar + repo URL verified via GitHub API.
- Entrypoint (README-backed): `make build`.

## Main

- Start in readonly access levels where possible; only widen permissions after you confirm the tool call surface is correct.
- Keep Azure credential directories and kubeconfig paths explicit and mounted read-only in containerized setups.
- Record tool calls that mutate clusters (create/update/delete) and require human approval for production contexts.

### README excerpt (source)

```text
# AKS-MCP

[![SafeSkill 92/100](https://img.shields.io/badge/SafeSkill-92%2F100_Verified%20Safe-brightgreen)](https://safeskill.dev/scan/azure-aks-mcp)
The AKS-MCP is a Model Context Protocol (MCP) server that enables AI assistants
to interact with Azure Kubernetes Service (AKS) clusters. It serves as a bridge
between AI tools (like GitHub Copilot, Claude, and other MCP-compatible AI
assistants) and AKS, translating natural language requests into AKS operations
and returning the results in a format the AI tools can understand.

It allows AI tools to:

- Operate (CRUD) AKS resources
- Retrieve details related to AKS clusters (VNets, Subnets, NSGs, Route Tables, etc.)
- Manage Azure Fleet operations for multi-cluster scenarios

## How it works

AKS-MCP connects to Azure using the Azure SDK and provides a set of tools that
AI assistants can use to interact with AKS resources. It leverages the Model
Context Protocol (MCP) to facilitate this communication, enabling AI tools to
make API calls to Azure and interpret the responses.

## Azure CLI Authentication

AKS-MCP uses Azure CLI (az) for AKS operations. Azure CLI authentication is attempted in this order:
```

### FAQ

**Q: Can I enable it via Docker UI?**
A: The README documents enabling the server via Docker Desktop MCP Toolkit and configuring mounts/paths.

**Q: What transport does it use?**
A: The README shows stdio transport examples for MCP client configuration.

**Q: What should I test first?**
A: Start with inventory/listing and read-only queries before allowing write operations.

## Source & Thanks

> Source: https://github.com/Azure/aks-mcp
> License: MIT
> GitHub: 132 stars · 37 forks · pushed 2026-05-12


---

<!-- ZH -->

## 快速使用

```bash
git clone https://github.com/Azure/aks-mcp && cd aks-mcp
make build
# 在 MCP 客户端里配置运行构建出的 `aks-mcp` 二进制，并传入：--transport stdio
```

## 简介

用 AKS-MCP 让助手理解与操作 AKS 集群，把请求转换为受控的 MCP 工具调用。

AKS-MCP 用于把支持 MCP 的助手桥接到 Azure Kubernetes Service 操作；可通过 Docker MCP Toolkit 启用，或在本地用 `make build` 从源码构建并以 stdio 方式接入。

**适合谁：** 负责 AKS 运维的平台团队，希望把集群盘点/排障/变更以 MCP 工具面暴露给助手

**可搭配：** Go 工具链（本地构建），Azure 凭证目录与 kubeconfig 路径，使用 stdio 传输的 MCP 客户端

**上手时间：** 约 15–30 分钟（鉴权 + 构建/工具箱 + 客户端配置）

### 关键事实（已验证）

- GitHub：132 stars · 37 forks · 最近更新 2026-05-12。
- 许可证：MIT（GitHub API 已验证仓库 URL / 头像等基础信息）。
- 入口命令（基于 README）：`make build`。

## 主要内容

- 能只读就先只读；确认工具面与调用链路正确后，再逐步扩大权限。
- 容器化运行时把 Azure 凭证目录与 kubeconfig 路径显式挂载，并尽量只读挂载。
- 对会改动集群的调用（create/update/delete）做审计记录，并在生产场景引入人工确认。

### README 摘录（来源）

```text
# AKS-MCP

[![SafeSkill 92/100](https://img.shields.io/badge/SafeSkill-92%2F100_Verified%20Safe-brightgreen)](https://safeskill.dev/scan/azure-aks-mcp)
The AKS-MCP is a Model Context Protocol (MCP) server that enables AI assistants
to interact with Azure Kubernetes Service (AKS) clusters. It serves as a bridge
between AI tools (like GitHub Copilot, Claude, and other MCP-compatible AI
assistants) and AKS, translating natural language requests into AKS operations
and returning the results in a format the AI tools can understand.

It allows AI tools to:

- Operate (CRUD) AKS resources
- Retrieve details related to AKS clusters (VNets, Subnets, NSGs, Route Tables, etc.)
- Manage Azure Fleet operations for multi-cluster scenarios

## How it works

AKS-MCP connects to Azure using the Azure SDK and provides a set of tools that
AI assistants can use to interact with AKS resources. It leverages the Model
Context Protocol (MCP) to facilitate this communication, enabling AI tools to
make API calls to Azure and interpret the responses.

## Azure CLI Authentication

AKS-MCP uses Azure CLI (az) for AKS operations. Azure CLI authentication is attempted in this order:
```

### FAQ

**Q: 能用 Docker 图形界面启用吗？**
A: README 说明了通过 Docker Desktop 的 MCP Toolkit 启用并配置挂载路径。

**Q: 用什么传输方式？**
A: README 给出了以 stdio transport 接入 MCP 客户端的示例。

**Q: 应该先测试什么？**
A: 先从盘点/只读查询开始，确认稳定后再开放写操作。

## 来源与感谢

> 来源：https://github.com/Azure/aks-mcp
> 许可证：MIT
> GitHub：132 stars · 37 forks · 最近更新 2026-05-12



---
Source: https://tokrepo.com/en/workflows/aks-mcp-mcp-bridge-for-azure-kubernetes
Author: MCP Hub