Run a Google-grounded web search via Gemini and return the answer text.
AI agents call web_search to retrieve information from Gemini Search MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a web search and returns results—a classic read operation with no side effects, no code execution, no data modification, and no destructive actions. The search itself is a query operation that retrieves existing information. Severity is low because misuse would only expose publicly available information or generate harmless search queries.
From the tool's definition Tool name 'web_search' and description 'Run a Google-grounded web search via Gemini and return the answer text' indicate retrieval of search results. The verb 'return' and context of 'answer text' confirm data retrieval with no modifications.
Attacks that exploit this kind of access
Run a Google-grounded web search via Gemini and return the answer text. It is categorised as a Read tool in the Gemini Search MCP MCP Server, which means it retrieves data without modifying state.
Register the Gemini Search MCP server in PolicyLayer and add a rule for web_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 Gemini Search MCP. Nothing to install.
web_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 web_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 web_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.
web_search is provided by the Gemini Search MCP server (mimiclab/geminisearchmcp). 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 →