AI agents call get_pods 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 information about pods within a specified namespace. It is a read-only operation that queries cluster state without making changes, executing commands, or deleting resources. Even in a Kubernetes context where tools can be dangerous, this particular tool only fetches data about pod resources, making it a standard Read category operation with minimal security impact.
From the tool's definition Tool name 'get_pods' and description 'Get pods in a namespace' indicate a query/retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
Get pods in a namespace. 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 get_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 kube-MCP. Nothing to install.
get_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 get_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 get_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.
get_pods 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 →