Kai (Kubernetes) MCP server for AI agents

The Kubernetes MCP server (Kai) provides a bridge between large language model clients and your Kubernetes clusters, enabling interaction with Kubernetes resources through natural language. With Kai, you can manage pods, deployments, services, and namespaces using LLM clients like Claude or Ollama.

Requirements

Before installing Kai, ensure you have access to a Kubernetes cluster configured for kubectl (such as minikube, Rancher Desktop, EKS, GKE, etc.). The server will connect to your current context by default.

Installation

Install the Kubernetes MCP server with the following command:

go install github.com/basebandit/kai/cmd/kai

Configuration

Integration with Claude for Desktop

To add the server to your Claude for Desktop configuration:

Open the configuration file:

code ~/Library/Application\ Support/Claude/claude_desktop_config.json

Add the Kai server to your configuration:

{
  "mcpServers": {
    "kubernetes": {
      "command": "/path/to/kai binary"
    }
  }
}

Replace /path/to/kai binary with the actual path to the installed Kai executable.

Available Features

Kai currently supports the following Kubernetes operations:

Pod Management

Create pods
List pods
Get pod details
Delete pods
Stream pod logs

Deployment Management

Create deployments
List deployments
Describe deployments
Update deployments

Service Management

Create services
Get service details
List services
Delete services

Namespace Management

Create namespaces
List namespaces
Update namespaces
Delete namespaces

Usage Examples

Once configured, you can interact with your Kubernetes cluster through your LLM client using natural language commands. For example:

"List all pods in the default namespace"
"Create a new deployment called 'nginx' with 3 replicas using the nginx:latest image"
"Show logs for the pod named 'web-frontend'"
"Delete the service called 'api-gateway'"

The Kai MCP server will interpret these natural language requests and execute the appropriate Kubernetes commands on your behalf.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "kubernetes" '{"command":"kai"}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "kubernetes": {
            "command": "kai"
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "kubernetes": {
            "command": "kai"
        }
    }
}

3. Restart Claude Desktop for the changes to take effect