在互联网上搜索信息，返回相关的网页链接和摘要
AI agents call web_search to retrieve information from Web Search MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Web search is a read-only operation that queries public information and returns results without creating, modifying, deleting, or executing any side effects. The blast radius is minimal since search results do not alter any state or trigger external actions beyond retrieving information.
From the tool's definition Tool description states '搜索信息，返回相关的网页链接和摘要' (search for information, return relevant webpage links and summaries). The tool only retrieves and returns data with no modification of any resources.
Attacks that exploit this kind of access
在互联网上搜索信息，返回相关的网页链接和摘要. It is categorised as a Read tool in the Web Search MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Web Search MCP 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 Web Search MCP 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 Web Search MCP Server MCP server (mantraa-zzz/web_search). 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 →