What is kubernetes-mcp-server?

The Kubernetes MCP Server is a powerful and flexible Model Context Protocol server, enabling AI agents to interact directly with Kubernetes and OpenShift clusters. It provides a Go-based native implementation for comprehensive resource management, including Pod operations, Helm charts, and Tekton pipelines, without external dependencies.

Is kubernetes-mcp-server open source?

Yes, licensed under Apache-2.0.

kubernetes-mcp-server

Active·★ 2.2k·Apache-2.0·Updated 2026-10-13

★ Trending★ Essential

This is an MCP server implementation for Kubernetes and OpenShift. Its README lists automatic detection of changes in the kubeconfig (or in-cluster configuration), generic create, update, get, list and delete operations on any Kubernetes or OpenShift resource, and pod-specific operations such as listing, getting and deleting pods. The README is long (over 65k characters) and goes on to cover tools, configuration options, demos such as diagnosing and fixing an OpenShift deployment, and development notes.

The only requirement is access to a Kubernetes cluster. For Claude Desktop, VS Code and Cursor, the README gives an `npx` entry using `kubernetes-mcp-server@latest`, and Claude Code has a dedicated getting-started guide plus a separate guide for a locked-down, read-only ServiceAccount setup. The CLI can be run through `npx`, `uvx` or a downloaded release binary, and configuration is done with command-line arguments. It is published on npm and PyPI under the name `kubernetes-mcp-server` and is Apache-2.0 licensed.

#Kubernetes#OpenShift#MCP Server#Container Orchestration#Cloud Native#API Integration#Go#DevOps#AI Agent

Features

01Go-based native implementation: Directly interacts with Kubernetes API server, avoiding `kubectl`/`helm` wrapper overhead.

02Comprehensive resource management: Supports CRUD operations on any Kubernetes/OpenShift resource, including Pods, Namespaces, Events, Helm, and Tekton.

03Lightweight and Cross-Platform: Distributed as a single native binary for Linux, macOS, and Windows, also available as npm, Python, and Docker packages.

04Multi-Cluster support: Capable of interacting with multiple Kubernetes clusters simultaneously as defined in kubeconfig files.

05Configurable and Observability-ready: Supports CLI arguments, TOML config files, environment variables, and optional OpenTelemetry tracing/metrics.

Why choose it

+Works with any Kubernetes or OpenShift resource through generic CRUD, plus pod-specific tools

+Picks up kubeconfig changes automatically

+Runs from `npx`, `uvx` or a release binary, with ready-made config for Claude Desktop, VS Code and Cursor

+A documented read-only ServiceAccount setup for safer production use

Trade-offs

!Giving an AI client write access to a cluster is risky; use the read-only setup and review destructive actions before approving

!The README is very long, so finding the exact options takes time

!Requires working cluster access and sensible RBAC on your side

!Tool behavior depends on the model's choices; verify before running changes on production clusters

Compatibility

Runtime

Verified via docs

Node.js

Runtime

Verified via docs

Python

Runtime

Verified via docs

Linux

Verified via docs

macOS

Verified via docs

Windows

Verified via docs

Quick start

$ npx -y kubernetes-mcp-server@latest

Use cases

↳Integrate AI agents (e.g., Claude Desktop, VS Code, Cursor, Goose CLI) with Kubernetes for intelligent cluster management and automation.

↳Automate diagnosis and resolution of issues in OpenShift Deployments using AI-driven analysis and corrective actions.

↳Streamline application deployment and development workflows on Kubernetes/OpenShift with AI assistance, such as 'Vibe Coding' and GitHub Copilot integration.

↳Perform advanced Kubernetes operations like managing Helm releases, starting Tekton pipelines, and viewing detailed resource metrics through a unified MCP interface.

↳Enable secure and controlled access for AI tools to Kubernetes clusters by configuring read-only mode, denied resources, and specific toolsets.

Alternatives

GitHub MCP Server★ 33.6k

GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).

python-sdk★ 24.6k

The official Python SDK for Model Context Protocol servers and clients

ragflow★ 92.2k

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Gemini CLI★ 107.3k

An open-source AI agent that brings the power of Gemini directly into your terminal. Supports native MCP.

Open Interpreter★ 68.6k

A coding agent for the terminal, optimized for low-cost and open models. Forked from OpenAI's Codex, it can emulate other agent harnesses and runs commands in a native sandbox.

GPT Researcher★ 30.1k

An autonomous agent that conducts deep research on any data using any LLM provider, producing detailed reports with citations from web and local sources.

BotSharp★ 3.1k

AI Multi-Agent Framework in .NET

claudian★ 15.7k

An Obsidian plugin that embeds AI coding agents (Claude Code, Codex CLI, OpenCode and more) in your vault, with the vault as the agent's working directory.

See all alternatives →

Comments

No comments yet. Be the first!

kubernetes-mcp-server

Active·★ 2.2k·Apache-2.0·Updated 2026-10-13

★ Trending★ Essential

#Kubernetes#OpenShift#MCP Server#Container Orchestration#Cloud Native#API Integration#Go#DevOps#AI Agent

Features

01Go-based native implementation: Directly interacts with Kubernetes API server, avoiding `kubectl`/`helm` wrapper overhead.

02Comprehensive resource management: Supports CRUD operations on any Kubernetes/OpenShift resource, including Pods, Namespaces, Events, Helm, and Tekton.

03Lightweight and Cross-Platform: Distributed as a single native binary for Linux, macOS, and Windows, also available as npm, Python, and Docker packages.

04Multi-Cluster support: Capable of interacting with multiple Kubernetes clusters simultaneously as defined in kubeconfig files.

05Configurable and Observability-ready: Supports CLI arguments, TOML config files, environment variables, and optional OpenTelemetry tracing/metrics.

Why choose it

+Works with any Kubernetes or OpenShift resource through generic CRUD, plus pod-specific tools

+Picks up kubeconfig changes automatically

+Runs from `npx`, `uvx` or a release binary, with ready-made config for Claude Desktop, VS Code and Cursor

+A documented read-only ServiceAccount setup for safer production use

Trade-offs

!Giving an AI client write access to a cluster is risky; use the read-only setup and review destructive actions before approving

!The README is very long, so finding the exact options takes time

!Requires working cluster access and sensible RBAC on your side

!Tool behavior depends on the model's choices; verify before running changes on production clusters

Compatibility

Runtime

Verified via docs

Node.js

Runtime

Verified via docs

Python

Runtime

Verified via docs

Linux

Verified via docs

macOS

Verified via docs

Windows

Verified via docs

Quick start

$ npx -y kubernetes-mcp-server@latest

Use cases

↳Integrate AI agents (e.g., Claude Desktop, VS Code, Cursor, Goose CLI) with Kubernetes for intelligent cluster management and automation.

↳Automate diagnosis and resolution of issues in OpenShift Deployments using AI-driven analysis and corrective actions.

↳Streamline application deployment and development workflows on Kubernetes/OpenShift with AI assistance, such as 'Vibe Coding' and GitHub Copilot integration.

↳Perform advanced Kubernetes operations like managing Helm releases, starting Tekton pipelines, and viewing detailed resource metrics through a unified MCP interface.

↳Enable secure and controlled access for AI tools to Kubernetes clusters by configuring read-only mode, denied resources, and specific toolsets.

Alternatives

GitHub MCP Server★ 33.6k

GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).

python-sdk★ 24.6k

The official Python SDK for Model Context Protocol servers and clients

ragflow★ 92.2k

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Gemini CLI★ 107.3k

An open-source AI agent that brings the power of Gemini directly into your terminal. Supports native MCP.

Open Interpreter★ 68.6k

A coding agent for the terminal, optimized for low-cost and open models. Forked from OpenAI's Codex, it can emulate other agent harnesses and runs commands in a native sandbox.

GPT Researcher★ 30.1k

An autonomous agent that conducts deep research on any data using any LLM provider, producing detailed reports with citations from web and local sources.

BotSharp★ 3.1k

AI Multi-Agent Framework in .NET

claudian★ 15.7k

An Obsidian plugin that embeds AI coding agents (Claude Code, Codex CLI, OpenCode and more) in your vault, with the vault as the agent's working directory.

See all alternatives →

Comments

No comments yet. Be the first!