AI agents use update_dashboard to create or update resources in Newrelic — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Newrelic environment.
The tool performs a reversible modification operation (updating a dashboard) rather than deletion. While the description is empty, the function name clearly indicates a Write operation that creates or modifies data. In a monitoring/observability platform like New Relic, dashboard updates affect visibility and alerting configurations but are not irreversible or destructive.
From the tool's definition Tool name is 'update_dashboard' on a New Relic MCP server. The name indicates modification of dashboard configuration or content.
Attacks that exploit this kind of access
update_dashboard. It is categorised as a Write tool in the Newrelic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Newrelic MCP server in PolicyLayer and add a rule for update_dashboard: 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.
update_dashboard is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_dashboard 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 update_dashboard. 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.
update_dashboard 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 →