Get a NewRelic dashboard with full page and widget details. Returns the dashboard structure including all pages, their widgets, and widget configurations. Use this to understand dashboard layout and widget queries.
AI agents call get_dashboard to retrieve information from NewRelic MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries dashboard data without side effects. It does not create, modify, delete, or execute any operations—it only fetches and displays existing dashboard information. This is a classic read operation with minimal risk if misused by an AI agent, as the worst case would be unauthorized information disclosure of dashboard layouts and configurations.
From the tool's definition Tool name 'get_dashboard' and description states it 'Get[s] a NewRelic dashboard' and 'Returns the dashboard structure including all pages, their widgets, and widget configurations.' The verbs are retrieval-focused ('Get', 'Returns') with no modification,…
Attacks that exploit this kind of access
Get a NewRelic dashboard with full page and widget details. Returns the dashboard structure including all pages, their widgets, and widget configurations. Use this to understand dashboard layout and widget queries. It is categorised as a Read tool in the NewRelic MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NewRelic MCP Server MCP server in PolicyLayer and add a rule for get_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 MCP Server. Nothing to install.
get_dashboard 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_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 get_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.
get_dashboard is provided by the NewRelic MCP Server MCP server (ruminaider/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 →