AI agents call search_xhs_users to retrieve information from Xiaohongshu API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only search operation that queries and returns user data. It has no side effects, does not modify any data, and does not execute code or trigger external operations beyond retrieving existing information. The blast radius if misused is low—an AI agent could retrieve public user information but could not modify, delete, or cause financial harm.
From the tool's definition Tool name is 'search_xhs_users' and description translates to 'Search Xiaohongshu users by keyword.' The operation retrieves user information based on search queries without modifying, deleting, or executing actions on the platform.
Documented attack patterns abuse exactly the kind of access search_xhs_users gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Xiaohongshu API MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_xhs_users:
{
"version": "1",
"default": "deny",
"tools": {
"search_xhs_users": {}
}
}search_xhs_users is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
根据关键词搜索小红书用户。. It is categorised as a Read tool in the Xiaohongshu API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Xiaohongshu API MCP Server MCP server in PolicyLayer and add a rule for search_xhs_users: 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 API MCP Server. Nothing to install.
search_xhs_users 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_xhs_users 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_xhs_users. 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_xhs_users is provided by the Xiaohongshu API MCP Server MCP server (proerror77/xhs_mcp_agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Xiaohongshu API MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Xiaohongshu API MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.