kubectl-ai
AI powered Kubernetes Assistant
kubectl-ai is an AI-powered Kubernetes assistant that operates as both an MCP server and client, translating natural language queries into precise Kubernetes operations. Developed by GoogleCloudPlatform, it exposes kubectl and bash tools through the Model Context Protocol, enabling AI agents to manage Kubernetes clusters conversationally. The tool supports multiple LLM providers including Gemini, OpenAI, Vertex AI, AWS Bedrock, and local models via Ollama. It features both interactive chat mode and single-command execution, with configurable tool sets and session persistence.
Key Features
Use Cases
- 01Enabling Claude Desktop or Cursor to manage Kubernetes clusters through natural language queries
- 02Creating a unified MCP endpoint that combines Kubernetes operations with general-purpose tools from other MCP servers
- 03Running AI-assisted kubectl operations in CI/CD pipelines or automated workflows
- 04Providing conversational Kubernetes troubleshooting and log analysis for operations teams
- 05Building custom Kubernetes automation tools with AI assistance using the MCP client mode
- 06Deploying secure authenticated MCP endpoints for team-wide AI-powered cluster management
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-ai — FAQ
What is kubectl-ai MCP server?+
kubectl-ai is an MCP server that exposes Kubernetes management tools (kubectl and bash) to AI clients like Claude Desktop or Cursor, enabling natural language control of Kubernetes clusters. It can also act as an MCP client to consume tools from other MCP servers.
How do I install kubectl-ai as an MCP server?+
Download the binary from the releases page or use the quick install script (curl -sSL https://raw.githubusercontent.com/GoogleCloudPlatform/kubectl-ai/main/install.sh | bash), then run 'kubectl-ai --mcp-server' to start it in MCP server mode. You can also install via Krew (kubectl krew install ai) or use the provided Docker image.
Which AI clients work with kubectl-ai?+
kubectl-ai works with any MCP-compatible client including Claude Desktop, Cursor, and VS Code when run in MCP server mode. It also functions as a standalone CLI tool with support for Gemini, OpenAI, Azure OpenAI, Grok, and AWS Bedrock.
Do I need API keys to use kubectl-ai?+
Yes, you need an API key for your chosen LLM provider (GEMINI_API_KEY for Google's Gemini by default, OPENAI_API_KEY for OpenAI, etc.). You can also use local models via Ollama or llama.cpp without external API keys. A configured kubectl context is required to manage Kubernetes clusters.
Is kubectl-ai free to use?+
kubectl-ai itself is free and open-source under an Apache-style license. However, you'll incur costs from your chosen LLM provider (Gemini, OpenAI, etc.) based on their pricing, unless you use free local models via Ollama.
Can kubectl-ai connect to other MCP servers?+
Yes, kubectl-ai supports MCP client mode (--mcp-client flag) to consume tools from external MCP servers configured in ~/.config/kubectl-ai/mcp.yaml. It can also run in enhanced server mode (--mcp-server --external-tools) to aggregate and re-expose those external tools alongside its native kubectl tools.
How do I install kubectl-ai?+
Open the source repository on GitHub and follow its README. kubectl-ai is a mcp server — MCP Agents Market links you directly to the official repo.
Is kubectl-ai free?+
kubectl-ai is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.