AI agents call search to retrieve information from WebSearch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Web search tools retrieve and query information from the internet without creating, modifying, or deleting data. This is a read-only operation with no side effects. The empty description reduces confidence slightly, but the tool name and server purpose clearly indicate information retrieval. Severity is low because search results are read-only outputs with minimal risk of harm from misuse.
From the tool's definition Tool named 'search' on a web search server with capabilities for 'web search, content extraction, web crawling, and scraping.' The name and server context indicate data retrieval without modification.
Attacks that exploit this kind of access
search. It is categorised as a Read tool in the WebSearch MCP Server, which means it retrieves data without modifying state.
Register the WebSearch MCP server in PolicyLayer and add a rule for 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 WebSearch. Nothing to install.
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 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 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.
search is provided by the WebSearch MCP server (josemartinrodriguezmortaloni/websearch-tools). 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 →