AI agents call get_application_metrics to retrieve information from Newrelic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about available metrics for an application without creating, modifying, deleting, or executing operations. It has no side effects and presents minimal risk even if misused by an agent, as it only exposes information about what metrics exist rather than sensitive metric data itself or the ability to alter system state.
From the tool's definition Tool name 'get_application_metrics' and description 'Get available metrics for an application' indicate a query/retrieval operation with no side effects. The verb 'get' and action 'retrieve metrics' are characteristic of Read operations.
Attacks that exploit this kind of access
Get available metrics for an application. It is categorised as a Read tool in the Newrelic MCP Server, which means it retrieves data without modifying state.
Register the Newrelic MCP server in PolicyLayer and add a rule for get_application_metrics: 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 Newrelic. Nothing to install.
get_application_metrics 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_application_metrics 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_application_metrics. 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_application_metrics is provided by the Newrelic MCP server (@piekstras/newrelic-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 →