AI agents invoke query_nrql to trigger actions in Newrelic. 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.
This tool executes arbitrary query statements, which could include data-modifying or data-exposing operations depending on NRQL capabilities. Even if primarily read-oriented, executing arbitrary query language falls under Execute due to the open-ended nature of what can be run.
From the tool's definition "Execute an NRQL query" — the tool runs arbitrary NRQL (New Relic Query Language) statements against New Relic data infrastructure.
Attacks that exploit this kind of access
Execute an NRQL query. It is categorised as a Execute tool in the Newrelic MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Newrelic MCP server in PolicyLayer and add a rule for query_nrql: 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.
query_nrql 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_nrql 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_nrql. 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_nrql 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 →