SSyncDev

Kubernetes MCP Server

Kubernetes MCP server with the top30 tools

Local serverstdioPython

What is the Kubernetes MCP server?

Most cloud and infrastructure work still happens through a UI a human drives. Kubernetes MCP server moves it into the conversation instead. Kubernetes MCP server with the top30 tools.

The short version

This project provides a Kubernetes MCP (Model Context Protocol) server built using FastMCP and the official Kubernetes Python client. It exposes a wide range of Kubernetes management and inspection tools as MCP tools, making it easy to interact with your Kubernetes or OpenShift cluster programmatically or via GitHub Copilot.

  • Pod Management — List, describe, and get logs for pods
  • Deployment Management — List, scale, and inspect deployments
  • Service Management — List and get details of services
  • Namespace Management — List, create, and delete namespaces
  • Node Management — List and describe nodes
  • ConfigMap & Secret Management — List and get ConfigMaps and Secrets

Getting it running

Installation goes through your MCP client rather than a global install: point it at fastmcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

What it needs from you

  • Python 3.x - fastmcp - kubernetes Python client - kubectl (for cluster access) - Access to a Kubernetes or OpenShift cluster (kubeconfig or in-cluster config)

How it compares

Among the cloud and infrastructure options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes.

This entry was verified against Kubernetes's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How to install the Kubernetes MCP server

{
  "mcpServers": {
    "github-com-vp1099-vp1099-kubernetes": {
      "command": "uvx",
      "args": ["fastmcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.x - fastmcp - kubernetes Python client - kubectl (for cluster access) - Access to a Kubernetes or OpenShift cluster (kubeconfig or in-cluster config)

Frequently asked questions

It connects Kubernetes to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Kubernetes directly.

Alternatives to the Kubernetes MCP server

Supabase

Official

Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.

DatabasesRemoteTypeScript★ 2.2k

n8n

Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.

Developer ToolsRemoteTypeScript★ 22.5k

AWS

Official

AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.

Cloud & DevOpsPython★ 7.0k

Browserbase

Official

Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.

Browser AutomationRemoteTypeScript★ 2.9k

Cloudflare

Official

Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.

Cloud & DevOpsRemoteTypeScript★ 2.9k

Grafana

Official

Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.

Monitoring & ObservabilityGo★ 1.7k