AI agents call list_resources 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.
List operations retrieve and display existing resources without modification, deletion, or execution of commands. This is a standard Read operation on Kubernetes clusters. Low severity because listing resources alone does not directly compromise systems, though it does enumerate infrastructure which could inform further attacks. Confidence is high based on tool naming convention despite empty description.
From the tool's definition Tool name 'list_resources' indicates a listing/enumeration operation typical of read-only queries. Pattern consistent with sibling tools like 'describe_pod' which are informational.
Attacks that exploit this kind of access
list_resources. 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 list_resources: 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.
list_resources 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 list_resources 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 list_resources. 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.
list_resources 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 →