Recent Warning events in a namespace — key signal for incident diagnosis
AI agents call get_events to retrieve information from Kubernetes + Prometheus SRE MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves event data from a Kubernetes cluster for diagnostic purposes. It has no side effects, does not modify cluster state, does not execute commands, and does not delete or move resources. It is a passive monitoring/observability tool used for incident diagnosis.
From the tool's definition Tool name is 'get_events' with description 'Recent Warning events in a namespace' — a retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
Recent Warning events in a namespace — key signal for incident diagnosis. It is categorised as a Read tool in the Kubernetes + Prometheus SRE MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kubernetes + Prometheus SRE MCP Server MCP server in PolicyLayer and add a rule for 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 + Prometheus SRE MCP Server. Nothing to install.
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 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 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.
get_events is provided by the Kubernetes + Prometheus SRE MCP Server MCP server (manishmaurya22/sre-mcp-server). 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 →