A Model Context Protocol server that lets AI assistants query multiple Kubernetes clusters simultaneously using natural language.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.CLUSTER_NAME— Yes Name for this cluster — must match a key in CLUSTER_TOKENS on the serverCLUSTER_TOKENS— Yes JSON object mapping cluster names to tokens: {"prod":"token1","staging":"token2"}HEALTH_PORTINSECURE_TLS— No Set to true to skip TLS verification (dev only, never in production)LOG_LEVEL— No Pino log level (default: info)MAX_AGENT_CONNECTIONS_PER_IP— No Max WebSocket connections per source IP (default: 10)MCP_API_KEY— No API key for MCP clients. If unset, the MCP endpoint is open to anyone who can reach it.PORT— No HTTP port (default: 3000)[](https://m8ven.ai/mcp/youssofkhawaja-kube-mcp-1mucvx)