AI agents call xhs_user_notes to retrieve information from Xhs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries publicly available user content and engagement data without any side effects. It performs a GET-like operation to fetch existing data. No data is created, modified, deleted, or executed. The blast radius of misuse is minimal—an agent could retrieve user content at scale, but cannot harm systems or data.
From the tool's definition Tool description states 'Get all published notes from a specific Xiaohongshu user' and 'Returns their content portfolio with engagement metrics.' The server is described as 'read-only access' with capabilities for 'search, note details, user profiles, and…
Attacks that exploit this kind of access
Get all published notes from a specific Xiaohongshu user. Returns their content portfolio with engagement metrics. Useful for analyzing a creator. It is categorised as a Read tool in the Xhs MCP Server, which means it retrieves data without modifying state.
Register the Xhs MCP server in PolicyLayer and add a rule for xhs_user_notes: 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 Xhs. Nothing to install.
xhs_user_notes 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_user_notes 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_user_notes. 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_user_notes is provided by the Xhs MCP server (xyj2570/xhs-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 →