Search Google for a query
AI agents call search_google to retrieve information from MCP Deep Web Research Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves search results from Google based on a user query. It has no side effects on data, does not execute code or shell commands, does not create or modify records, and does not delete anything. It is a pure read operation that queries an external service and returns results.
From the tool's definition Tool name is 'search_google' and description states 'Search Google for a query' — a straightforward information retrieval operation with no modification, deletion, or execution of code or commands.
Attacks that exploit this kind of access
Search Google for a query. It is categorised as a Read tool in the MCP Deep Web Research Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Deep Web Research Server 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 MCP Deep Web Research Server. 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 MCP Deep Web Research Server MCP server (pedrodnt/mcp-deepwebresearch). 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 →