Error rate analysis
AI agents call metrics.getErrors to retrieve information from Kubernetes MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves monitoring/observability data (error rates) from the Kubernetes cluster for diagnostic purposes. It performs data retrieval with no capability to modify resources, execute commands, delete data, or affect cluster state. This is consistent with the read-only nature of the parent server's monitoring and troubleshooting functionality.
From the tool's definition Tool name 'metrics.getErrors' with description 'Error rate analysis' indicates querying or retrieving metric data about errors without modifying any system state or executing operations.
Attacks that exploit this kind of access
Error rate analysis. It is categorised as a Read tool in the Kubernetes MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kubernetes MCP Server MCP server in PolicyLayer and add a rule for metrics.getErrors: 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. Nothing to install.
metrics.getErrors 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 metrics.getErrors 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 metrics.getErrors. 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.
metrics.getErrors is provided by the Kubernetes MCP Server MCP server (kishanrao92/infra-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 →