MCP Kubernetes runs on your own machine — the client starts it, so there is no endpoint to ping. 399 installs a week from npm. Last commit 30 Aug 2026.
Kubernetes monitoring & ops for AI agents — safe-by-default access modes and guards.
Today is the operative word: we check MCP Kubernetes every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-kubernetes -- npx -y @dockndevai/mcp-kubernetes
{
"mcpServers": {
"mcp-kubernetes": {
"args": [
"-y",
"@dockndevai/mcp-kubernetes"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-kubernetes]
command = "npx"
args = ["-y", "@dockndevai/mcp-kubernetes"]
{
"mcpServers": {
"mcp-kubernetes": {
"args": [
"-y",
"@dockndevai/mcp-kubernetes"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-kubernetes": {
"args": [
"-y",
"@dockndevai/mcp-kubernetes"
],
"command": "npx"
}
}
}
Manage Percona PostgreSQL + PgBouncer on Kubernetes — safe-by-default access modes and guards.
Safe Kubernetes access for AI agents via MCP. Read-only by default, with explicit permission modes.
Operate a k3s / Kubernetes cluster from your AI agent — safe-by-default MCP server.
SSH & Kubernetes access broker for AI agents; the model never touches a credential.
Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit.
Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit.
Kubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.
Kubernetes RCA agent that sandboxes its own AI with OPA Gatekeeper. MCP-ready for any client.
Answers built from our own checks of this server.