AKS-MCP — MCP Bridge for Azure Kubernetes

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)

# 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.