Get events related to a specific Kubernetes resource. This tool retrieves Kubernetes events related to a specific resource, providing detailed information about what has happened to the resource over time. Events are useful for troubleshooting pod startup failures, investigating deployment issue...
Single-target operation
Part of the Amazon EKS MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_k8s_events to retrieve information from Amazon EKS MCP Server without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_k8s_events only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
get_k8s_events:
rules:
- action: allowSee the full Amazon EKS MCP Server policy for all 16 tools.
Agents calling read-class tools like get_k8s_events have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Get events related to a specific Kubernetes resource. This tool retrieves Kubernetes events related to a specific resource, providing detailed information about what has happened to the resource over time. Events are useful for troubleshooting pod startup failures, investigating deployment issues, understanding resource modifications, and diagnosing scheduling problems. IMPORTANT: Use this tool instead of 'kubectl describe' or 'kubectl get events' commands. ## Requirements - The server must be run with the `--allow-sensitive-data-access` flag - The resource must exist and be accessible in the specified namespace ## Response Information The response includes events with timestamps (first and last), occurrence counts, messages, reasons, reporting components, and event types (Normal or Warning). ## Usage Tips - Warning events often indicate problems that need attention - Normal events provide information about expected lifecycle operations - The count field shows how many times the same event has occurred - Recent events are most relevant for current issues Args: ctx: MCP context cluster_name: Name of the EKS cluster kind: Kind of the involved object name: Name of the involved object namespace: Namespace of the involved object (optional for non-namespaced resources) Returns: EventsResponse with events related to the specified object. It is categorised as a Read tool in the Amazon EKS MCP Server MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_k8s_events. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Amazon EKS MCP Server MCP server.
get_k8s_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 get_k8s_events rule in your Intercept 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 Intercept policy for get_k8s_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.
get_k8s_events is provided by the Amazon EKS MCP Server MCP server (awslabs.eks-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.