search_google_ads
Structured Google Ads Transparency pull for ONE advertiser (by domain or advertiserId) — use when you know the brand; use research_ads for open-ended research. Deliberately fetches the cheap BASIC listing (get_ad_details=false, ~1 credit — the detailed variant with per-ad headlines costs 25 credi...
This record as markdown: /tools/hermoso/search-google-ads.md
What search_google_ads does on Hermoso
AI agents call search_google_ads to retrieve information from Hermoso without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why search_google_ads is rated Low
This tool retrieves publicly available ad transparency data from Google Ads library for competitive research purposes. It performs no modifications, deletions, executions, or financial transactions—it only queries and returns structured advertising metadata. The low blast radius (data is already public via Google's ad library) and read-only nature confirm Read category with low severity.
From the tool's definition Tool description explicitly states it "fetches" and "returns" data in structured format (JSON) with fields like advertiser, format, adUrl, image, firstShown, lastShown. The verb 'pull' and 'fetches' indicate data retrieval.
Attacks that exploit this kind of access
The rule that runs search_google_ads safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Hermoso, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For search_google_ads, this is the rule to start with:
search_google_ads is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Hermoso, apply this rule, and every search_google_ads call is checked against it from then on.
Questions about search_google_ads
Structured Google Ads Transparency pull for ONE advertiser (by domain or advertiserId) — use when you know the brand; use research_ads for open-ended research. Deliberately fetches the cheap BASIC listing (get_ad_details=false, ~1 credit — the detailed variant with per-ad headlines costs 25 credits/call and is not exposed here). Returns compact JSON {advertiser, format, adUrl, image, firstShown, lastShown} per ad. It is categorised as a Read tool in the Hermoso MCP Server, which means it retrieves data without modifying state.
Register the Hermoso MCP server in PolicyLayer and add a rule for search_google_ads: 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 Hermoso. Nothing to install.
search_google_ads is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_google_ads 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 search_google_ads. 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.
search_google_ads is provided by the Hermoso MCP server (https://app.hermoso.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Hermoso, and thousands of servers like it.
This server
Across the catalogue