Execute a custom NRQL query against New Relic APM data.
AI agents invoke query-apm to trigger actions in New Relic MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes arbitrary NRQL queries, which means it runs user-supplied query logic against New Relic's APM data. While NRQL is primarily a read/analytics language, 'execute a custom query' implies running arbitrary code/queries whose effects depend on arguments. The blast radius is medium as it is scoped to APM data retrieval, but misuse could expose sensitive performance and application data.
From the tool's definition "Execute a custom NRQL query against New Relic APM data"
Attacks that exploit this kind of access
Execute a custom NRQL query against New Relic APM data. It is categorised as a Execute tool in the New Relic MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the New Relic MCP Server MCP server in PolicyLayer and add a rule for query-apm: 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 New Relic MCP Server. Nothing to install.
query-apm is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the query-apm 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 query-apm. 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.
query-apm is provided by the New Relic MCP Server MCP server (xelber/newrelic-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 →