ga4.custom_metrics.create · Ads MCP: Risk & Policy

WHAT IT DOES

What ga4.custom_metrics.create does on Ads

AI agents use ga4.custom_metrics.create to create or update resources in Ads — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ads environment.

WHY IT NEEDS A POLICY

Why ga4.custom_metrics.create needs a policy

This tool creates a new custom metric configuration on a GA4 property, which is a reversible write operation (metrics can be deleted/archived). It does not execute code, destroy data irreversibly, or involve financial transactions. Severity is medium because miscreated metrics could pollute analytics configuration across a property, but damage is limited and recoverable.

From the tool's definition 'Create a custom metric on a GA4 property' — creates a new resource; 'Dry-run by default' confirms it can perform real writes when dry-run is disabled.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ga4.custom_metrics.create Rate-limited

ga4.custom_metrics.create stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ga4.custom_metrics.create": {
      "limits": [
        {
          "counter": "ga4.custom_metrics.create_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Ads, so you can run agents against it safely.

FAQ

Questions about ga4.custom_metrics.create

What does the ga4.custom_metrics.create tool do? +

Create a custom metric on a GA4 property. Required fields: parameter_name, display_name, measurement_unit. Dry-run by default. It is categorised as a Write tool in the Ads MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ga4.custom_metrics.create? +

Register the Ads MCP server in PolicyLayer and add a rule for ga4.custom_metrics.create: 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 Ads. Nothing to install.

What risk level is ga4.custom_metrics.create? +

ga4.custom_metrics.create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit ga4.custom_metrics.create? +

Yes. Add a rate_limit block to the ga4.custom_metrics.create 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 ga4.custom_metrics.create completely? +

Set action: deny in the PolicyLayer policy for ga4.custom_metrics.create. 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 ga4.custom_metrics.create? +

ga4.custom_metrics.create is provided by the Ads MCP server (manlikemuneeb/ads-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.