AI agents invoke nerdgraph_query 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 runs arbitrary NerdGraph GraphQL queries supplied by the caller. GraphQL mutations can create, modify, or delete resources across the entire New Relic account (alerts, dashboards, data, configurations, etc.). Because the query is user-defined and can include destructive mutations, the blast radius is very high.
From the tool's definition "Execute a custom NerdGraph GraphQL query" — the word 'Execute' and 'custom' indicate arbitrary GraphQL operations
Attacks that exploit this kind of access
Execute a custom NerdGraph GraphQL 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 nerdgraph_query: 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.
nerdgraph_query 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 nerdgraph_query 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 nerdgraph_query. 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.
nerdgraph_query 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 →