Execute metric queries on Datadog. Specify the metric name and optional filters/aggregations to build and execute the query.
AI agents call get_metrics to retrieve information from Datadog 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 metrics data from Datadog for analysis purposes. While it uses 'execute' in the description, it is executing a query (querying/fetching data), not executing arbitrary code or triggering external operations with unpredictable side effects. The tool has no capability to modify, delete, or create metrics—only to read them. Therefore, it belongs in the Read category.
From the tool's definition Tool executes metric queries on Datadog to retrieve data; description states 'Specify the metric name and optional filters/aggregations to build and execute the query' which indicates data retrieval without modification or deletion.
Documented attack patterns abuse exactly the kind of access get_metrics gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Datadog MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_metrics:
{
"version": "1",
"default": "deny",
"tools": {
"get_metrics": {}
}
} get_metrics is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute metric queries on Datadog. Specify the metric name and optional filters/aggregations to build and execute the query. It is categorised as a Read tool in the Datadog MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Datadog MCP Server MCP server in PolicyLayer and add a rule for get_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 MCP Server. Nothing to install.
get_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 get_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 get_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.
get_metrics is provided by the Datadog MCP Server MCP server (shelfio/datadog-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Datadog MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Datadog MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.