Query Datadog metrics data for a specified time range. Returns
AI agents call query_metrics to retrieve information from MCP Datadog Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries metrics data from Datadog without side effects. It does not create, modify, delete, or execute code—it simply fetches monitoring data. The low severity reflects minimal blast radius if misused by an AI agent, as it can only access information already available in the monitoring system.
From the tool's definition Tool name 'query_metrics' and description 'Query Datadog metrics data for a specified time range. Returns' indicate data retrieval without modification.
Attacks that exploit this kind of access
Query Datadog metrics data for a specified time range. Returns. It is categorised as a Read tool in the MCP Datadog Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Datadog Server MCP server in PolicyLayer and add a rule for query_metrics: 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 MCP Datadog Server. Nothing to install.
query_metrics 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 query_metrics 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_metrics. 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_metrics is provided by the MCP Datadog Server MCP server (micaelmalta/mcp-server-datadog). 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 →