Fetch recent cluster events, optionally filtered by namespace or involved object.
AI agents call tool_k8s_get_events to retrieve information from Kubernetes MCP Server – 5G Core Edition without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries Kubernetes cluster event data (e.g., pod scheduling, node status changes, warnings). It has no side effects, does not execute code or commands, and does not modify cluster state. It is a passive inspection/diagnostic tool.
From the tool's definition Tool name and description: 'Fetch recent cluster events' — retrieves event logs without modification or execution of external operations.
Attacks that exploit this kind of access
Fetch recent cluster events, optionally filtered by namespace or involved object. It is categorised as a Read tool in the Kubernetes MCP Server – 5G Core Edition MCP Server, which means it retrieves data without modifying state.
Register the Kubernetes MCP Server – 5G Core Edition MCP server in PolicyLayer and add a rule for tool_k8s_get_events: 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 Kubernetes MCP Server – 5G Core Edition. Nothing to install.
tool_k8s_get_events 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 tool_k8s_get_events 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 tool_k8s_get_events. 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.
tool_k8s_get_events is provided by the Kubernetes MCP Server – 5G Core Edition MCP server (sanzco/mcp5g). 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 →