AI agents use update_experiment_arm 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.
The tool appears to modify experiment arm settings (a reversible change) rather than execute arbitrary operations, delete data, or move money. In Google Ads, experiment arms are configurations that can be updated and reverted. This is categorized as Write rather than Execute because it modifies structured advertising data rather than running code or triggering external side-effect operations.
From the tool's definition Tool name 'update_experiment_arm' indicates modification of experiment configuration. Server description states it 'wraps the Google Ads API v20, enabling AI agents to manage campaigns, budgets, keywords, conversions' — updating experiment arms fits this…
Documented attack patterns abuse exactly the kind of access update_experiment_arm 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 update_experiment_arm:
{
"version": "1",
"default": "deny",
"tools": {
"update_experiment_arm": {
"limits": [
{
"counter": "update_experiment_arm_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_experiment_arm 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.
update_experiment_arm. 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 update_experiment_arm: 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.
update_experiment_arm 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 update_experiment_arm 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 update_experiment_arm. 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.
update_experiment_arm 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.