AI agents use mutate_experiment_arms to create or update resources in Google Ads — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google Ads environment.
This tool modifies experiment arm configurations within Google Ads campaigns, which constitutes a reversible write operation. While the empty description limits certainty, the 'mutate_' prefix is standard Google Ads API nomenclature for write operations (as opposed to 'create_', 'get_', or 'delete_').
From the tool's definition Tool name 'mutate_experiment_arms' indicates modification of experiment arms within Google Ads. The 'mutate' prefix is a Google Ads API convention for write operations that alter campaign experiment configurations.
Documented attack patterns abuse exactly the kind of access mutate_experiment_arms gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google Ads, and nothing reaches the server without passing your rules. This is the rule we recommend for mutate_experiment_arms:
{
"version": "1",
"default": "deny",
"tools": {
"mutate_experiment_arms": {
"limits": [
{
"counter": "mutate_experiment_arms_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mutate_experiment_arms 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.
Free to start. No card required.
mutate_experiment_arms. It is categorised as a Write tool in the Google Ads MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google Ads MCP server in PolicyLayer and add a rule for mutate_experiment_arms: 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 Google Ads. Nothing to install.
mutate_experiment_arms is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mutate_experiment_arms 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 mutate_experiment_arms. 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.
mutate_experiment_arms is provided by the Google Ads MCP server (promobase/google-ads-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Google Ads, 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.
59 Google Ads tools catalogued and risk-classified — across an index of 43,000+ MCP servers.