AI agents call get_application_metric_data 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 metric data from New Relic without any side effects. It is a read-only operation that queries existing monitoring data. The 'Get' verb and absence of any language suggesting data modification, deletion, or code execution clearly place it in the Read category.
From the tool's definition Tool name is 'get_application_metric_data' and description states 'Get metric data for an application' — uses the verb 'Get' indicating a retrieval operation with no modification or execution.
Attacks that exploit this kind of access
Get metric data 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_metric_data: 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_metric_data 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_metric_data 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_metric_data. 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_metric_data 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 →