AI agents invoke google_ads_custom_query to trigger actions in Google Ads MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The server description explicitly references 'custom GAQL queries', indicating this tool runs arbitrary user-supplied queries against Google Ads. GAQL can be used for both read and mutating operations depending on the query. Since the description is empty and the tool could execute arbitrary queries (including modifications), Execute is the most appropriate category.
From the tool's definition Tool name contains 'custom_query'; server description mentions 'custom GAQL queries' — GAQL (Google Ads Query Language) allows arbitrary query execution against Google Ads data and potentially mutating operations.
Documented attack patterns abuse exactly the kind of access google_ads_custom_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google Ads MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for google_ads_custom_query:
{
"version": "1",
"default": "deny",
"tools": {
"google_ads_custom_query": {
"limits": [
{
"counter": "google_ads_custom_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} google_ads_custom_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
google_ads_custom_query. It is categorised as a Execute tool in the Google Ads MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Google Ads MCP Server MCP server in PolicyLayer and add a rule for google_ads_custom_query: 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 MCP Server. Nothing to install.
google_ads_custom_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the google_ads_custom_query 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 google_ads_custom_query. 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.
google_ads_custom_query is provided by the Google Ads MCP Server MCP server (johnoconnor0/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 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.
142 Google Ads MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.