Bridge Your AI Assistant to Kubernetes Clusters

Stop context-switching between your AI chat and terminal windows. This MCP server connects Claude (or any MCP-compatible AI) directly to your Kubernetes clusters, letting you manage deployments, troubleshoot pods, and inspect cluster state through natural language commands.

The Problem with K8s Management

You're debugging a production issue at 2 AM. Your AI assistant suggests checking pod logs and scaling a deployment, but you need to:

1. Alt-tab to your terminal
2. Remember the exact kubectl syntax
3. Type out the namespace and resource names
4. Copy-paste the output back to your AI chat
5. Repeat this dance for every operation

There's a better way.

Direct Cluster Access from Your AI Assistant

With this MCP server, your AI can execute kubectl and Helm commands directly. Ask Claude to "scale my nginx deployment to 5 replicas" or "show me the logs for failing pods in the api namespace" and watch it happen in real-time.

What you get:

• Complete kubectl integration - All the operations you use daily: get, describe, apply, delete, logs, scale, patch, rollout
• Helm management - Install, upgrade, and manage charts without leaving your chat
• Smart troubleshooting - Built-in diagnostic flows that systematically investigate pod issues
• Port forwarding - Set up local access to cluster services on demand
• Context awareness - Automatically uses your current kubectl context and config

Real-World Scenarios Where This Shines

Production Debugging: "Check the health of all pods in the payment-service namespace and show me logs for any that are failing." Your AI executes the commands and provides a comprehensive status report.

Deployment Management: "Apply this YAML manifest to staging and then check if the rollout completed successfully." No more switching between chat and terminal to paste manifests and verify deployments.

Infrastructure Scaling: "The API pods are under heavy load. Scale the deployment to 10 replicas and monitor the status." Your AI handles both the scaling operation and the follow-up verification.

Cluster Exploration: "What ingress controllers are running and what services are they exposing?" Perfect for onboarding to new environments or investigating unfamiliar clusters.

Safety First with Non-Destructive Mode

Enable read-only mode when you want your AI to inspect and analyze without making changes:

{
  "mcpServers": {
    "kubernetes-readonly": {
      "command": "npx",
      "args": ["mcp-server-kubernetes"],
      "env": {
        "ALLOW_ONLY_NON_DESTRUCTIVE_TOOLS": "true"
      }
    }
  }
}

Your AI can still get cluster information, describe resources, view logs, and even apply configurations, but destructive operations like kubectl delete are blocked.

Seamless Integration

Works with your existing setup - no cluster modifications required. The server uses your current kubectl configuration and respects your RBAC permissions. If you can run kubectl get pods, the MCP server can too.

Claude Desktop setup:

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

Command line testing:

npx mcp-chat --server "npx mcp-server-kubernetes"

Built for Real Kubernetes Workflows

• Multi-cluster support through kubectl contexts
• Namespace-aware operations with automatic filtering
• YAML manifest handling for GitOps workflows
• Helm chart management including custom values and repositories
• Advanced troubleshooting with the built-in k8s-diagnose prompt
• Resource scaling and patching for operational tasks

This isn't a toy for simple demos. It's a production-ready tool that handles the complexity of real Kubernetes environments while giving you the conversational interface you want for cluster management.

Stop copying and pasting between terminals and chat windows. Give your AI direct access to your clusters and watch your K8s productivity soar.