Perform a Google search and return formatted results
AI agents call search_google to retrieve information from Google Toolbox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search and returns results—a classic read-only operation with no state mutations, code execution, or resource consumption beyond standard query costs. The low severity reflects minimal blast radius; misuse would only return unwanted information, not cause damage or unauthorized actions.
From the tool's definition Tool name 'search_google' and description 'Perform a Google search and return formatted results' indicate a query operation that retrieves search results without modifying, executing code, or causing side effects.
Documented attack patterns abuse exactly the kind of access search_google gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google Toolbox, and nothing reaches the server without passing your rules. This is the rule we recommend for search_google:
{
"version": "1",
"default": "deny",
"tools": {
"search_google": {}
}
}search_google 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.
Perform a Google search and return formatted results. It is categorised as a Read tool in the Google Toolbox MCP Server, which means it retrieves data without modifying state.
Register the Google Toolbox MCP server in PolicyLayer and add a rule for search_google: 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 Toolbox. Nothing to install.
search_google 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 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. 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 is provided by the Google Toolbox MCP server (jikime/py-mcp-google-toolbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Google Toolbox, 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.
11 Google Toolbox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.