K8scortex MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 306 installs a week from npm. Last commit 27 Oct 2026.
Kubernetes MCP server: 75 tools for GKE, AKS, EKS, RBAC, audit logging, GitOps, multi-cluster.
We read the source, 5 d ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
const tokenEndpoint = process.env.IDENTITY_ENDPOINT || "http://169.254.169.254/metadata/identity/oauth2/token";
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch K8scortex MCP and you get told the day something new turns up.
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 k8scortex-mcp -- npx -y k8scortex-mcp
{
"mcpServers": {
"k8scortex-mcp": {
"command": "npx",
"args": [
"-y",
"k8scortex-mcp"
]
}
}
}
[mcp_servers.k8scortex-mcp]
command = "npx"
args = ["-y", "k8scortex-mcp"]
{
"mcpServers": {
"k8scortex-mcp": {
"command": "npx",
"args": [
"-y",
"k8scortex-mcp"
]
}
}
}
{
"servers": {
"k8scortex-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"k8scortex-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
KUBECONFIG (Path to your kubeconfig file. Each context becomes a cluster. Defaults to ~/.kube/config), CLUSTERS_CONFIG (Optional path to a cluster registry JSON file mixing kubeconfig, EKS, GKE and Key Vault clusters), K8SCORTEX_STDIO_ROLES (Roles for the local session, e.g. 'developer' for read-only tools. Defaults to platform-engineer).
MCP server for natural-language Kubernetes operations across single or multi-cluster environments.
Kubernetes MCP server for diagnosis, resource management, GitOps, and RBAC-enforced operations.
OpenShift/Kubernetes cluster management via the oc CLI for MCP clients
Kubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.
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.
MimiOps is an opinionated MCP server for Kubernetes
Governed Kubernetes ops — 55 MCP tools with audit, budget, undo, risk-tier audit labels.
Answers built from our own checks of this server.