AI agents call list_service_accounts to retrieve information from K8s without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries Kubernetes ServiceAccount metadata in a namespace or cluster-wide scope. It has no side effects, does not create, modify, or delete resources, and does not execute commands or trigger external operations. While ServiceAccount information could potentially inform privilege escalation attacks in a multi-tenant environment, the tool itself is purely informational (Read category).
From the tool's definition Tool name and description indicate 'List ServiceAccounts' which retrieves and queries Kubernetes resources without modification. The verb 'list' is explicitly a Read operation per the classification rules.
Attacks that exploit this kind of access
List ServiceAccounts in a namespace or across all namespaces. It is categorised as a Read tool in the K8s MCP Server, which means it retrieves data without modifying state.
Register the K8s MCP server in PolicyLayer and add a rule for list_service_accounts: 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. Nothing to install.
list_service_accounts 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_service_accounts 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_service_accounts. 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_service_accounts is provided by the K8s MCP server (jingyanjiang/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 →