Query Datadog metrics. Actions: - query: Get timeseries data (requires from/to time range, PromQL query) - search: Find metrics by name (grep-like, NO time param needed) - list: Get recently active metrics (last 24h, optionally filter by tag) - metadata: Get metric details (unit, type, descriptio...
Risk signalsAdmin/system-level operation
Part of the Datadog server.
Free to start. No card required.
AI agents call metrics to retrieve information from Datadog without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though metrics only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"metrics": {}
}
}See the full Datadog policy for all 23 tools.
These attack patterns abuse exactly the kind of access metrics gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Query Datadog metrics. Actions: - query: Get timeseries data (requires from/to time range, PromQL query) - search: Find metrics by name (grep-like, NO time param needed) - list: Get recently active metrics (last 24h, optionally filter by tag) - metadata: Get metric details (unit, type, description) APM METRICS (auto-generated from traces): Keyed by OPERATION name (e.g. express.request, pg.query), NOT service name. Filter by service using tags: {service:my-service} PERCENTILES (p50/p75/p90/p95/p99) \u2014 use the ROOT metric (distribution type): p95:trace.express.request{service:my-service} AVG/SUM/MIN/MAX \u2014 use the .duration SUFFIX (pre-aggregated gauge): avg:trace.express.request.duration{service:my-service} Other trace metrics (gauges): - trace.<operation>.hits - Request count - trace.<operation>.errors - Error count - trace.<operation>.apdex - Apdex score To discover operation names for a service, use: traces tool with action. It is categorised as a Read tool in the Datadog MCP Server, which means it retrieves data without modifying state.
Register the Datadog MCP server in PolicyLayer and add a rule for 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 Datadog. Nothing to install.
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 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 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.
metrics is provided by the Datadog MCP server (datadog-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 23 Datadog tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.