kubectl-mcp-server
Published in CNCF Landscape: A MCP server for Kubernetes.
kubectl-mcp-server is an MCP server that enables natural language control of Kubernetes infrastructure through AI assistants. It exposes 253 tools for managing pods, deployments, services, Helm charts, security audits, cost optimization, and more across single or multi-cluster environments. Developers can troubleshoot crashes, deploy applications, audit RBAC, and visualize dashboards by conversing with Claude Desktop, Cursor, Windsurf, or other MCP-compatible clients. The server supports multiple transports (stdio, SSE, HTTP), includes optional interactive UI dashboards, browser automation, and integrates with GitOps tools, cert-manager, policy engines, and backup solutions.
Key Features
Use Cases
- 01Debug crashed or pending pods by asking AI to diagnose logs, events, and resource issues
- 02Deploy and scale applications using natural language instead of kubectl commands
- 03Perform security audits by requesting RBAC permission analysis and secret scanning across namespaces
- 04Optimize cluster costs by identifying idle resources and overprovisioned workloads
- 05Manage Helm charts with conversational install, upgrade, rollback, and value inspection
- 06Troubleshoot network connectivity issues between services and pods through AI-guided diagnostics
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
kubectl-mcp-server — FAQ
What is kubectl-mcp-server?+
kubectl-mcp-server is an MCP server that provides 253 Kubernetes management tools accessible through natural language conversations with AI assistants like Claude Desktop, Cursor, and Windsurf. It translates conversational requests into kubectl operations for managing pods, deployments, Helm charts, security, and more.
How do I install kubectl-mcp-server?+
Run npx -y kubectl-mcp-server (no installation needed) or install globally with npm install -g kubectl-mcp-server. Alternatively, install via pip with pip install kubectl-mcp-server or use Docker with docker pull rohitghumare64/kubectl-mcp-server:latest.
Which AI clients work with kubectl-mcp-server?+
It works with all MCP-compatible clients including Claude Desktop, Claude Code, Cursor, Windsurf, GitHub Copilot, Goose, Gemini CLI, Roo Code, and 15+ other AI assistants. Configuration examples are provided for each client.
What are the prerequisites for using kubectl-mcp-server?+
You need kubectl installed and configured with access to a Kubernetes cluster, plus either Node.js 14+ (for npx) or Python 3.9+ (for pip installation). No API keys are required, but the server uses your existing kubeconfig for cluster authentication.
Is kubectl-mcp-server free to use?+
Yes, kubectl-mcp-server is open source under the MIT license and free to use. It's available on PyPI, npm, and Docker Hub at no cost.
Can I manage multiple Kubernetes clusters?+
Yes, every tool supports an optional context parameter to target specific clusters without switching your kubectl context. You can also list and switch contexts using natural language commands.
How do I install kubectl-mcp-server?+
Open the source repository on GitHub and follow its README. kubectl-mcp-server is a mcp server — MCP Agents Market links you directly to the official repo.
Is kubectl-mcp-server free?+
kubectl-mcp-server is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.