AI agents call cluster_health to retrieve information from kube-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs health status checking, which is fundamentally a read operation that retrieves diagnostic information from the Kubernetes cluster. It has no side effects, does not execute arbitrary code, and does not modify, delete, or create resources. The blast radius of misuse is minimal—an agent could only retrieve health information, which poses no direct operational risk to the cluster.
From the tool's definition Tool name 'cluster_health' and description 'Check cluster health status' indicate a read-only operation that queries and retrieves cluster health information without modifying state.
Attacks that exploit this kind of access
Check cluster health status. It is categorised as a Read tool in the kube-MCP MCP Server, which means it retrieves data without modifying state.
Register the kube- MCP server in PolicyLayer and add a rule for cluster_health: 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 kube-MCP. Nothing to install.
cluster_health 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 cluster_health 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 cluster_health. 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.
cluster_health is provided by the kube- MCP server (siddjoshi/kube-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →