搜索小红书笔记
AI agents call xhs_search to retrieve information from Xiaohongshu without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves notes from Xiaohongshu platform. Search operations are read-only queries that do not create, modify, delete, or execute code. No irreversible changes or financial transactions are involved. The blast radius of misuse is minimal—an agent could retrieve unintended content, but this causes no harm to data or systems.
From the tool's definition Tool name 'xhs_search' and description '搜索小红书笔记' (search Xiaohongshu notes) indicate a search/query operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
搜索小红书笔记. It is categorised as a Read tool in the Xiaohongshu MCP Server, which means it retrieves data without modifying state.
Register the Xiaohongshu MCP server in PolicyLayer and add a rule for xhs_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 Xiaohongshu. Nothing to install.
xhs_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 xhs_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 xhs_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.
xhs_search is provided by the Xiaohongshu MCP server (lozzi1910/xiaohongshu-mcp). 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 →