AI agents call search_google to retrieve information from SearchAPI MCP Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries Google's search service and returns results to the user. It has no side effects on data—it only retrieves publicly available information. This is a classic Read operation. The low severity reflects minimal blast radius: misuse would only return search results, with no capability to modify systems, execute code, or cause financial harm.
From the tool's definition Tool description states '执行Google搜索' (perform Google search). The tool name 'search_google' and server context indicate this retrieves search results from Google. No modification, deletion, execution of arbitrary code, or financial operations are implied.
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 SearchAPI MCP Agent, 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.
执行Google搜索. It is categorised as a Read tool in the SearchAPI MCP Agent MCP Server, which means it retrieves data without modifying state.
Register the SearchAPI MCP Agent 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 SearchAPI MCP Agent. 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 SearchAPI MCP Agent MCP server (rmmargt/searchapi-mcp-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SearchAPI MCP Agent, 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.
9 SearchAPI MCP Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.