AI agents call list_services 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.
This tool retrieves information about Kubernetes services without modifying state. Despite the empty description, the naming convention strongly suggests a read-only query operation. The lack of description reduces confidence slightly, but 'list_*' patterns in Kubernetes tooling are standardly non-destructive retrieval operations with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'list_services' indicates a listing/query operation typical of Read category tools. No description provided, but 'list' operations in Kubernetes are non-mutating queries that retrieve service information without side effects.
Attacks that exploit this kind of access
list_services. 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_services: 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_services 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_services 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_services. 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_services 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 →