Retrieves CPU and memory usage metrics of pods (requires metrics-server)
AI agents call k8s.get_resource_usage to retrieve information from K8s Mcp Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns observability data (resource usage metrics) from a Kubernetes cluster without any side effects, modifications, or command execution. It is a straightforward read operation that fits the Read category. The read-only nature of the server and the retrieval semantics confirm low severity risk.
From the tool's definition Tool description states 'Retrieves CPU and memory usage metrics' with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Retrieves CPU and memory usage metrics of pods (requires metrics-server). It is categorised as a Read tool in the K8s Mcp Assistant MCP Server, which means it retrieves data without modifying state.
Register the K8s Mcp Assistant MCP server in PolicyLayer and add a rule for k8s.get_resource_usage: 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 K8s Mcp Assistant. Nothing to install.
k8s.get_resource_usage 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 k8s.get_resource_usage 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 k8s.get_resource_usage. 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.
k8s.get_resource_usage is provided by the K8s Mcp Assistant MCP server (nicolasmosquerar/k8s-mcp-assistant). 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 →