AI agents call google_search to retrieve information from Outscraper MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Google search is a read-only operation that retrieves publicly available information without modifying, deleting, or executing code. Despite the empty description creating some uncertainty (hence 0.7 confidence rather than higher), the tool name and server context strongly suggest data retrieval rather than write, execute, or destructive operations.
From the tool's definition Tool named 'google_search' with empty description; based on server context providing 'data extraction services' and sibling tools like 'google_maps_directions', 'company_insights', and review/product data retrieval, this appears to be a search/query tool for…
Documented attack patterns abuse exactly the kind of access google_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Outscraper MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for google_search:
{
"version": "1",
"default": "deny",
"tools": {
"google_search": {}
}
}google_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
google_search. It is categorised as a Read tool in the Outscraper MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Outscraper MCP Server MCP server in PolicyLayer and add a rule for google_search: 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 Outscraper MCP Server. Nothing to install.
google_search 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 google_search 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_search. 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_search is provided by the Outscraper MCP Server MCP server (outscraper/outscraper-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Outscraper 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.
28 Outscraper MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.