Kubernetes MCP server

This MCP server provides a bridge between Codename Goose AI agent and Kubernetes clusters, allowing you to interact with and manage Kubernetes resources through natural language commands. The server implements the Model Context Protocol (MCP) to facilitate communication between Goose and your Kubernetes environment.

Getting Started

Obtaining a Gemini API Key

To use this MCP server, you'll need a Gemini API key:

1. Visit https://aistudio.google.com/
2. Create an account and generate an API key
3. The model gemini-2.0-pro-exp-02-05 is currently available for free use

Installing Codename Goose

Codename Goose is required as it includes the MCP client that communicates with our server:

1. Follow the installation instructions at https://block.github.io/goose/docs/getting-started/installation
2. Set up the Gemini API key in your environment:

export GOOGLE_API_KEY=your_api_key_here

3. Configure Goose with:

goose configure

Setting Up the MCP Server

Prerequisites

Before installing the MCP server, ensure you have:

1. Python installed on your system
2. The uv package manager (recommended over pip)
3. A functioning Kubernetes cluster (Minikube for local development)

Installing Minikube

For local development, install Minikube:

# For Linux x86-64 systems
curl -LO https://storage.googleapis.com/minikube/releases/latest/minikube-linux-amd64
sudo install minikube-linux-amd64 /usr/local/bin/minikube

Start your Minikube cluster:

minikube start

Installing the MCP Server

1. Clone the repository:

git clone https://github.com/[username]/kube-mcp.git
cd kube-mcp

2. Install dependencies using uv:

uv pip install -r requirements.txt

3. Test the server:

mcp dev server.py

Using the MCP Server

Connecting to Goose

To connect the MCP server to Codename Goose:

1. Start a new Goose session with the kube-mcp extension:

goose session --with-builtin developer --with-extension "uvx kube-mcp"

Example Usage

Once connected, you can interact with your Kubernetes cluster using natural language commands in Goose:

> List all pods in the default namespace

> Create a new deployment with 3 replicas of nginx

> Scale the nginx deployment to 5 replicas

The MCP server translates these commands into Kubernetes API calls using the kubernetes-client/python library and your cluster's configuration.

Troubleshooting

Kubernetes Configuration

If you experience connection issues, verify that:

1. Your Kubernetes config is properly loaded
2. Minikube is running: minikube status
3. Your kubeconfig is in the default location or specified correctly

MCP Server Connectivity

If Goose cannot connect to your MCP server:

1. Ensure the server is running: mcp dev server.py
2. Check that the extension is properly specified in your Goose session command
3. Look for any error messages in the MCP server logs

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 "kube-mcp" '{"command":"uvx","args":["kube-mcp"]}'

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": {
        "kube-mcp": {
            "command": "uvx",
            "args": [
                "kube-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 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": {
        "kube-mcp": {
            "command": "uvx",
            "args": [
                "kube-mcp"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect