MCP-K8sWizard

🤖 AI-powered Kubernetes management with 37+ tools via natural language. Transform complex Kubectl commands into simple conversations. Perfect for DevOps teams using VSCode / Cursor AI. Built with Go.

go

3

GitHub Stars

go

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "heniv96-mcp-k8swizard": {
      "command": "/path/to/mcp-k8swizard",
      "args": [
        "--verbose"
      ]
    }
  }
}

MCP-K8sWizard is an MCP server that provides AI-powered, natural language interfaces for Kubernetes operations. It enables you to manage clusters, monitor resources, and troubleshoot tasks through conversational prompts, while supporting multi-cluster contexts and RBAC-aware workflows.

How to use

You interact with the MCP-K8sWizard server through an MCP client. Start by ensuring your MCP client can reach the local or remote MCP server, then speak natural language prompts to perform cluster management, resource operations, diagnostics, and scaling tasks. The server exposes a rich set of tools organized into Kubernetes operations, kubectl-like actions, context management, and AI-guided guidance. Use simple, task-focused prompts to perform actions such as checking cluster health, listing resources, viewing logs, scaling deployments, and diagnosing issues. The system will guide you through steps when troubleshooting and provide suggestions tailored to your current context.

How to install

Prerequisites: You need a Go toolchain and access to a Kubernetes cluster. Ensure kubeconfig is configured and you have permission to access your clusters.

Step-by-step setup is illustrated by the following commands.

git clone https://github.com/heniv96/mcp-k8swizard.git
cd mcp-k8swizard
make install

# Configure Cursor AI with the MCP server entry shown below in your Cursor AI settings
# In Cursor AI, add a MCP entry at ~/.cursor/mcp.json with the following snippet.

{
  "mcpServers": {
    "k8s-wizard": {
      "command": "/path/to/mcp-k8swizard",
      "args": ["--verbose"]
    }
  }
}

Continue setup

Restart Cursor AI after saving the MCP entry, then begin using natural language prompts to interact with Kubernetes resources through MCP-K8sWizard.

Available tools

k8s_cluster_info

Retrieve high-level information about Kubernetes clusters, including version, nodes, and statuses.

k8s_check_all_clusters

Check health and readiness across all connected clusters and surface any issues.

ping

Perform connectivity checks to Kubernetes API endpoints or other MCP components.

k8s_list_resources

List resources across namespaces or specific resource types.

k8s_get_resource

Fetch detailed information for a single Kubernetes resource.

k8s_get_logs

Retrieve logs for pods, containers, or deployments.

k8s_get_events

Show recent events and state changes in the cluster.

k8s_exec_in_pod

Execute commands inside a running pod for debugging.

k8s_natural_language_query

Translate natural language questions into Kubernetes queries or actions.

kubectl_get

Retrieve resources using kubectl-style read operations.

kubectl_describe

Show detailed descriptions of resources.

kubectl_create

Create new resources from definitions or inline specs.

kubectl_apply

Apply configuration changes to resources.

kubectl_delete

Delete resources by name, type, or label.

kubectl_context

Switch or view the current Kubernetes context.

kubectl_scale

Scale deployments or stateful sets to a desired replica count.

kubectl_patch

Patch resources to modify fields without full replacement.

kubectl_rollout

Manage application rollouts and view rollout status.

kubectl_generic

Execute generic kubectl commands beyond predefined helpers.

explain_resource

Explain the purpose and configuration of a Kubernetes resource.

list_api_resources

List available API resources and their capabilities.

k8s_set_context

Set the active multi-cluster context for subsequent commands.

k8s_get_current_context

Display the currently active context.

k8s_list_contexts

List all configured contexts for easy switching.

k8s_clear_context

Clear stored context information.

k8s_diagnose

Perform AI-guided diagnostics to identify problems.

k8s_troubleshoot

Step-by-step troubleshooting prompts for common issues.

k8s_optimize

Suggest optimizations for resource usage and configurations.

k8s_security

Assess and improve security posture across clusters.

k8s_performance

Monitor and optimize performance metrics.

k8s_deployment

Assist with deployment strategies and rollouts.

prompt_suggestions

Provide context-aware prompt suggestions for different scenarios.