Low Risk

get_metric_field_values

Get all possible values for a specific field of a metric from Datadog to discover available dimensions

How to control get_metric_field_values ↓

What get_metric_field_values does on Datadog MCP Server

AI agents call get_metric_field_values 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.

Low Risk

Why get_metric_field_values needs a policy

This tool queries Datadog to retrieve metadata about metric dimensions—it fetches information to help users discover what values exist for a metric field. This is a pure read operation with no capability to modify, delete, or execute actions. The blast radius of misuse is minimal, as an agent could only exhaust query limits or discover information already accessible in the monitoring system.

From the tool's definition Tool name 'get_metric_field_values' and description 'Get all possible values for a specific field of a metric from Datadog to discover available dimensions' indicate data retrieval with no modification or side effects.

Documented attack patterns abuse exactly the kind of access get_metric_field_values gives an agent:

How to control get_metric_field_values

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_metric_field_values:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_metric_field_values": {}
  }
}

get_metric_field_values is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Datadog MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about get_metric_field_values

What does the get_metric_field_values tool do? +

Get all possible values for a specific field of a metric from Datadog to discover available dimensions. It is categorised as a Read tool in the Datadog MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_metric_field_values? +

Register the Datadog MCP Server MCP server in PolicyLayer and add a rule for get_metric_field_values: 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.

What risk level is get_metric_field_values? +

get_metric_field_values is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_metric_field_values? +

Yes. Add a rate_limit block to the get_metric_field_values 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.

How do I block get_metric_field_values completely? +

Set action: deny in the PolicyLayer policy for get_metric_field_values. 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.

What MCP server provides get_metric_field_values? +

get_metric_field_values 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.

Enforce policy on every Datadog MCP Server tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.