Kai (Kubernetes) MCP server

Enables natural language interaction with Kubernetes clusters for managing pods, retrieving logs, and manipulating container environments without complex kubectl commands.
Back to servers
Provider
Evanson Mwangi
Release date
Mar 25, 2025
Language
Go
Stats
16 stars

The Kubernetes MCP Server (Kai) provides a bridge between language model clients like Claude and Ollama and your Kubernetes clusters, enabling cluster management through natural language. This server exposes tools for managing various Kubernetes resources including pods, deployments, and services.

Requirements

Before installation, ensure you have access to a Kubernetes cluster configured for kubectl. This can be a local development cluster (minikube, Rancher Desktop) or a cloud-based cluster (EKS, GKE, etc.). The server will connect to your current kubectl context by default.

Installation

Install the Kubernetes MCP server using Go:

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

Integration with Claude Desktop

To integrate with Claude Desktop, edit the configuration file:

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

Add the server to your configuration:

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

Available Features

Kai currently supports the following Kubernetes operations:

Pod Management

  • Create pods
  • List all pods
  • Get detailed pod information
  • Delete pods
  • Stream pod logs

Deployment Management

  • Create deployments
  • List all deployments
  • Describe deployment details
  • Update existing deployments

Service Management

  • Create services
  • Get service details
  • List all services
  • Delete services

Upcoming Features

Future releases will include support for:

  • Cluster management (connect, list, switch)
  • Namespace operations
  • Ingress configuration
  • ConfigMaps and Secrets management
  • Jobs and CronJobs
  • Node management
  • Utility functions
  • Persistent volume management
  • RBAC (Role-Based Access Control)
  • Custom resource operations

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later