k8s-interactive-mcp
Allows running kubectl commands to interact with Kubernetes clusters using a specified kubeconfig path, with support for command line piping and automatic interpretation of command results
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@k8s-interactive-mcp list all pods in the default namespace"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
k8s-interactive-mcp
A MCP server that can run Kubernetes commands with a given kubeconfig path and provide interpretation of the commands.
Result
Related MCP server: kubernetes-mcp-server
Features
Run kubectl commands through MCP tools
Flexible command line piping
Automatic kubectl installation check
Support for custom kubeconfig paths
Error handling and helpful messages
Usage
Install dependencies:
npm installBuild the server:
npm run buildFor development with auto-rebuild:
npm run watchInstallation
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"k8s-interactive": {
"command": "/path/to/k8s-interactive/build/index.js"
}
}
}Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspectorThe Inspector will provide a URL to access debugging tools in your browser.
Available Tools
1 toolrun_kubectl_commandC
Run a kubectl command against the cluster pointed to by the current kubeconfig
Inputs: command (required), kubeconfig (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as running kubectl commands, making it impossible for an agent to confuse it with another tool.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'run_kubectl_command' follows a clear verb_noun pattern, and there are no other tools to create inconsistency.
A single tool is too few for a Kubernetes management server, as it lacks coverage for common operations like listing resources, applying configurations, or checking cluster status. This forces agents to rely solely on raw kubectl commands, which is inefficient and error-prone for the domain.
The tool surface is severely incomplete for Kubernetes management. While 'run_kubectl_command' provides a generic entry point, it lacks dedicated tools for essential operations such as get, apply, delete, describe, or logs, leaving significant gaps that will cause agent failures in automated workflows.
Related MCP Connectors
An MCP server that let you interact with Cycloid.io Internal Development Portal and Platform
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceThis project is intended as a both MCP server connecting to Kubernetes and a library to build more servers for any custom resources in Kubernetes.382MIT
- AlicenseNot gradedqualityBmaintenanceA powerful and flexible Kubernetes MCP server implementation with support for OpenShift.2,243GoApache 2.0
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI assistants to interact with Kubernetes clusters by translating natural language into kubectl and Helm operations. It allows users to query, manage, and diagnose Kubernetes resources and cluster states through a seamless integration.20Apache 2.0
- AlicenseNot gradedqualityDmaintenanceAn MCP server that lets AI assistants safely inspect and operate on Kubernetes clusters through natural conversation.MIT