run_kubectl
Executes kubectl commands against a target cluster for read and write operations. Use it for actions not covered by dedicated tools such as scaling, model deployment, or Helm.
Instructions
Execute a kubectl command on a cluster.
Use this only for operations not covered by dedicated tools. Prefer scale_deployment to scale pods, deploy_model for model deployments, and helm_upgrade or helm_uninstall for Helm operations.
Reads always pass: get, describe, logs, top, rollout (status, history), api-resources, api-versions, explain, cluster-info, config (view), version, wait, auth (can-i).
Writes (delete, apply, patch, scale, label, cordon, drain, exec, …) pass unless the organisation's tool policy turned them off (allow_writes on run_kubectl / kubectl_exec in the console's Tool Policy, open by default). The policy engine asks for confirmed=True, records the write in the audit log, and runs it WITHOUT verification — the catalogued action for the same change would carry a proof, so prefer it when one exists. When the organisation turned writes off, the engine refuses the write by name, whatever the caller.
Args: cluster_name: Target cluster. command: kubectl arguments as a list, without the 'kubectl' prefix. Example: ["get", "pods", "-n", "default"] gateway_id: Gateway UUID from list_clusters. Omit for single-gateway deployments; provide to disambiguate when multiple gateways share a cluster name. confirmed: Required for a write. Pass False (default) to receive the confirmation request with its preview, or the refusal.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"cluster_name": "<cluster_name>",
"command": "<command>"
},
"name": "run_kubectl"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | ||
| confirmed | No | ||
| gateway_id | No | ||
| cluster_name | Yes |