Skip to content

Investigating using AKS MCP Server¶

You can investigate Azure Kubernetes Service issues using HolmesGPT with the AKS MCP (Model Context Protocol) server.

AKS MCP Integration

Prerequisites¶

Setting Up AKS MCP Server¶

Step 1: Setup the MCP Server¶

  • Open VS Code Command Palette (Ctrl+Shift+P or Cmd+Shift+P)
  • Run: "AKS: Setup AKS MCP Server"
  • Follow the setup wizard to configure your Azure credentials and cluster access

Step 2: Update Configuration for SSE¶

After installation, update your VS Code MCP configuration (.vscode/mcp.json) to use SSE transport and start the server 

{
  "servers": {
    "AKS MCP": {
      "command": "/Users/yourname/.vs-kubernetes/tools/aks-mcp/v0.0.3/aks-mcp",
      "args": [
        "--transport",
        "sse"
      ]
    }
  }
}
Note: Change "stdio" to "sse" in the transport argument.

Step 3: Configure HolmesGPT¶

Add this configuration to your HolmesGPT config file (~/.holmes/config.yaml):

mcp_servers:
  aks-mcp:
    description: "Azure Kubernetes Service(AKS) Model Context Protocol(MCP) server"
    url: "http://localhost:8000/sse"
    llm_instructions: "MCP server to get AKS cluster information, retrieve cluster resources and workloads, analyze network policies and VNet configurations, query control plane logs, fetch cluster metrics and health status. Investigate networking issues with NSGs and load balancers, perform kubectl operations, real-time monitoring of DNS, services across Azure Kubernetes environments"

Investigation Examples¶

Once configured, you can investigate AKS issues using natural language queries:

Cluster Health Issues¶

holmes ask "What issues do I have in my AKS cluster?"

Network Connectivity Problems¶

holmes ask "My payment deployment can't reach external services investigate why"

What's Next?¶