Guardrails for AI agents on your cluster: a local, policy-gated Kubernetes MCP server with RBAC-style, context-scoped access control. Point it at an over-privileged kubeconfig — it still can't nuke prod.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add kubeleash -- docker run -i --rm ghcr.io/kubeleash/kubeleash:0.3.0~/.codex/config.toml
[mcp_servers.kubeleash]
command = "docker"
args = ["run", "-i", "--rm", "ghcr.io/kubeleash/kubeleash:0.3.0"]
# codex mcp add kubeleash -- docker run -i --rm ghcr.io/kubeleash/kubeleash:0.3.0~/.cursor/mcp.json
{
"mcpServers": {
"kubeleash": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/kubeleash/kubeleash:0.3.0"
]
}
}
}.vscode/mcp.json
{
"servers": {
"kubeleash": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/kubeleash/kubeleash:0.3.0"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"kubeleash": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/kubeleash/kubeleash:0.3.0"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"kubeleash": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/kubeleash/kubeleash:0.3.0"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"kubeleash": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/kubeleash/kubeleash:0.3.0"
]
}
}
}