Escape hatch: run any raw GAQL query against Google Ads. Use when preset tools don
AI agents invoke gads_run_gaql to trigger actions in Google Ads. 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.
This tool allows execution of arbitrary GAQL (Google Ads Query Language) queries against a Google Ads account. It is an 'escape hatch' that bypasses the preset tools, enabling unrestricted query execution whose effects depend entirely on the query content. While the description is incomplete (cuts off mid-sentence), the core functionality is unmistakably Execute: it runs arbitrary queries against an external API.
From the tool's definition Escape hatch: run any raw GAQL query against Google Ads. Use when preset tools don[...]
Attacks that exploit this kind of access
Escape hatch: run any raw GAQL query against Google Ads. Use when preset tools don. It is categorised as a Execute tool in the Google Ads MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Google Ads MCP server in PolicyLayer and add a rule for gads_run_gaql: 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.
gads_run_gaql 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 gads_run_gaql 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 gads_run_gaql. 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.
gads_run_gaql is provided by the Google Ads MCP server (zleventer/google-ads-mcp-npm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →