Kubernetes MCP Server

What does “Kubernetes” MCP Server do?

The Kubernetes MCP Server is a Model Context Protocol (MCP) server that acts as an interface between AI assistants and Kubernetes or OpenShift clusters. It enables AI-driven tools and agents to interact programmatically with Kubernetes and OpenShift environments, streamlining development workflows that require cluster introspection, resource management, or operational automation. With the Kubernetes MCP Server, AI assistants can perform database-like queries against Kubernetes resources, manage pods and namespaces, execute commands within containers, and monitor resource usage. This enhances productivity for developers and operators by automating tasks such as viewing configurations, managing resources, and executing operational commands, helping bridge the gap between conversational AI and real-world cloud infrastructure management.

List of Prompts

No explicit prompt templates were found in the repository files or documentation.

List of Resources

• Kubernetes Configuration (.kube/config or in-cluster config):
  • Exposes the current Kubernetes configuration being used, allowing clients to read and use context for operations.
• Generic Kubernetes Resources:
  • Enables access to any Kubernetes or OpenShift resource for CRUD operations (Create/Update, Get, List, Delete).
• Pods:
  • Provides detailed resource information, status, logs, and metrics for Kubernetes pods.
• Namespaces:
  • Lists all available namespaces in the Kubernetes cluster for contextual queries and operations.

List of Tools

• View and Manage Kubernetes Configuration:
  • Allows viewing and updating the current Kubernetes configuration.
• CRUD Operations on Resources:
  • Create, update, get, list, or delete any Kubernetes or OpenShift resource.
• Pod Management:
  • List pods, get pod details, delete pods, show logs, fetch resource usage metrics, exec into pods, and run containers.
• Namespace Listing:
  • List all namespaces in the Kubernetes environment.

Use Cases of this MCP Server

• Kubernetes Resource Management:
  • Developers and operators can create, update, delete, or inspect any Kubernetes or OpenShift resource directly from an AI assistant, streamlining cluster management.
• Pod Operations and Monitoring:
  • Enables querying for pod status, accessing pod logs, monitoring resource usage, and executing commands inside pods for easier debugging and maintenance.
• Automated Namespace Management:
  • Quickly enumerate or manage namespaces for multi-tenant or organizational environments, supporting dynamic workflows.
• Cluster Configuration Inspection:
  • AI agents can review, validate, or update cluster configuration files (.kube/config), aiding in troubleshooting and change management.
• DevOps Task Automation:
  • Automate repetitive operational tasks (e.g., rolling deployments, scaling, monitoring) through conversational prompts with AI tools.

How to set it up

Windsurf

1. Ensure Node.js is installed and the Kubernetes MCP Server package is available.
2. Open or create the Windsurf configuration file.
3. Add the Kubernetes MCP Server using a JSON snippet in the mcpServers object.
4. Save the configuration and restart Windsurf.
5. Verify the setup by checking connectivity to your Kubernetes MCP Server.

{
  "mcpServers": {
    "kubernetes-mcp": {
      "command": "npx",
      "args": ["@kubernetes-mcp-server@latest"]
    }
  }
}

Securing API Keys

Use environment variables for sensitive information:

{
  "mcpServers": {
    "kubernetes-mcp": {
      "env": {
        "KUBECONFIG": "/path/to/your/kubeconfig"
      },
      "inputs": {}
    }
  }
}

Claude

1. Install Node.js and ensure access to the Kubernetes MCP Server.
2. Edit the Claude platform configuration file.
3. Add the MCP server JSON configuration.
4. Restart Claude platform.
5. Confirm the MCP server is operational.

{
  "mcpServers": {
    "kubernetes-mcp": {
      "command": "npx",
      "args": ["@kubernetes-mcp-server@latest"]
    }
  }
}

Securing API Keys

{
  "mcpServers": {
    "kubernetes-mcp": {
      "env": {
        "KUBECONFIG": "/path/to/your/kubeconfig"
      }
    }
  }
}

Cursor

1. Install Node.js.
2. Locate the Cursor configuration file.
3. Add the Kubernetes MCP Server entry in the mcpServers object.
4. Save and restart the Cursor platform.
5. Test connectivity to the Kubernetes MCP Server.

{
  "mcpServers": {
    "kubernetes-mcp": {
      "command": "npx",
      "args": ["@kubernetes-mcp-server@latest"]
    }
  }
}

Securing API Keys

{
  "mcpServers": {
    "kubernetes-mcp": {
      "env": {
        "KUBECONFIG": "/path/to/your/kubeconfig"
      }
    }
  }
}

Cline

1. Ensure Node.js is installed and the Kubernetes MCP Server is accessible.
2. Open the Cline configuration file.
3. Insert the MCP server configuration snippet.
4. Restart Cline.
5. Verify the setup is correct and the server is reachable.

{
  "mcpServers": {
    "kubernetes-mcp": {
      "command": "npx",
      "args": ["@kubernetes-mcp-server@latest"]
    }
  }
}

Securing API Keys

{
  "mcpServers": {
    "kubernetes-mcp": {
      "env": {
        "KUBECONFIG": "/path/to/your/kubeconfig"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "kubernetes-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “kubernetes-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

The Kubernetes MCP Server offers robust resource and operational management for Kubernetes/OpenShift via MCP, with excellent documentation and setup clarity. However, the lack of explicit sampling and prompt template support slightly limits its agentic flexibility. Overall, it is highly practical for DevOps/AI operations. Rating: 8/10

MCP Score