AI agents call high_restart_pods to retrieve information from Kubernetes Monitor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and filters pod information based on restart count thresholds. It has no side effects and cannot modify cluster state. The server itself is explicitly described as read-only, further confirming the classification.
From the tool's definition 'Find pods with high restart counts (>5)' — purely a query/filter operation; server is described as 'read-only MCP server for Kubernetes'
Documented attack patterns abuse exactly the kind of access high_restart_pods gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kubernetes Monitor, and nothing reaches the server without passing your rules. This is the rule we recommend for high_restart_pods:
{
"version": "1",
"default": "deny",
"tools": {
"high_restart_pods": {}
}
}high_restart_pods is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find pods with high restart counts (>5). It is categorised as a Read tool in the Kubernetes Monitor MCP Server, which means it retrieves data without modifying state.
Register the Kubernetes Monitor MCP server in PolicyLayer and add a rule for high_restart_pods: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Kubernetes Monitor. Nothing to install.
high_restart_pods is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the high_restart_pods rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for high_restart_pods. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
high_restart_pods is provided by the Kubernetes Monitor MCP server (vlttnv/k8s-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kubernetes Monitor, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 Kubernetes Monitor tools catalogued and risk-classified — across an index of 43,000+ MCP servers.