AI agents call get_pod_logs to retrieve information from K8s MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Retrieving pod logs is a read-only operation that queries existing data without modifying cluster state or executing commands. It has minimal blast radius—logs are informational and cannot cause infrastructure changes. Although the description is empty, the tool name is unambiguous and the context of sibling tools confirms this is a safe read operation.
From the tool's definition Tool name is 'get_pod_logs' which retrieves log data from pods. Server description mentions 'managing resources, deployments, and services' and sibling tools include read-only operations like 'describe_pod' and write/execute operations like 'apply_yaml' and…
Attacks that exploit this kind of access
get_pod_logs. It is categorised as a Read tool in the K8s MCP MCP Server, which means it retrieves data without modifying state.
Register the K8s MCP server in PolicyLayer and add a rule for get_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 K8s MCP. Nothing to install.
get_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 get_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 get_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.
get_pod_logs is provided by the K8s MCP server (rahul007-bit/k8s-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 →