google_search
AI agents call google_search to retrieve information from SerpApi 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 query operation that retrieves publicly available information with no side effects. It does not modify, delete, or execute code. Even if misused by an AI agent, it can only retrieve data that is already public, making the blast radius minimal. The low confidence deduction reflects the missing tool description, but the context is sufficiently clear.
From the tool's definition Tool name 'google_search' on a SerpAPI integration server that provides 'comprehensive search capabilities'.
Attacks that exploit this kind of access
google_search. It is categorised as a Read tool in the SerpApi MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SerpApi 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 SerpApi 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 SerpApi MCP Server MCP server (urdjmk/serpapi-mcp-server). 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 →