Search the internet using Google Custom Search.
AI agents call web_search to retrieve information from MCP Tool Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Web search retrieves and returns data from the internet with no side effects. It does not create, modify, delete, or execute code. While search results could theoretically be misused downstream, the tool itself is a pure read operation. The blast radius of misuse is low—the worst outcome would be retrieving unwanted information, not causing destructive or financial harm.
From the tool's definition Tool name is 'web_search' and description states 'Search the internet using Google Custom Search.' This is fundamentally a query operation that retrieves information without modifying, deleting, or executing operations on external systems.
Attacks that exploit this kind of access
Search the internet using Google Custom Search. It is categorised as a Read tool in the MCP Tool Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Tool Server 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 MCP Tool Server. 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 MCP Tool Server MCP server (sushma9903/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 →