AI agents call pod_logs 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 retrieves diagnostic information (pod logs) from a Kubernetes cluster without creating, modifying, or deleting any resources. It is a standard read operation that matches kubectl logs functionality. While logs may reveal sensitive information, the tool itself performs no mutation or destructive action. The blast radius of misuse is limited to information disclosure.
From the tool's definition Tool name 'pod_logs' and description 'Get logs from a pod' indicate data retrieval with no side effects. Logs are read-only outputs that cannot modify cluster state.
Attacks that exploit this kind of access
Get logs from a pod. 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 pod_logs: 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.
pod_logs 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 pod_logs 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 pod_logs. 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.
pod_logs 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 →