Retrieves a service and its endpoints to verify connectivity
AI agents call k8s.get_service_endpoints to retrieve information from K8s Mcp Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries Kubernetes service and endpoint information for inspection purposes. It performs a GET-style operation that retrieves existing data without creating, modifying, deleting, or executing anything. The server context reinforces this is read-only access intended for developers to inspect cluster state.
From the tool's definition Tool description states 'Retrieves a service and its endpoints' and server is explicitly described as 'read-only Kubernetes MCP server'. The verb 'retrieves' and the absence of mutation language confirm this is a query operation with no side effects.
Attacks that exploit this kind of access
Retrieves a service and its endpoints to verify connectivity. It is categorised as a Read tool in the K8s Mcp Assistant MCP Server, which means it retrieves data without modifying state.
Register the K8s Mcp Assistant MCP server in PolicyLayer and add a rule for k8s.get_service_endpoints: 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 Assistant. Nothing to install.
k8s.get_service_endpoints 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 k8s.get_service_endpoints 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 k8s.get_service_endpoints. 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.
k8s.get_service_endpoints is provided by the K8s Mcp Assistant MCP server (nicolasmosquerar/k8s-mcp-assistant). 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 →