AI agents call xhs_get_recent_notes to retrieve information from XHS-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a list of recently published notes from Xiaohongshu. It performs a read-only query operation that returns data without creating, modifying, deleting, executing code, or triggering financial transactions. The blast radius of misuse is minimal—an agent could only retrieve publicly available or user-owned note metadata, posing no irreversible harm.
From the tool's definition Tool name 'xhs_get_recent_notes' and description '获取近期已发布的笔记列表' (Get list of recently published notes) indicate retrieval/query of existing published content with no modification or execution of external operations.
Attacks that exploit this kind of access
获取近期已发布的笔记列表. It is categorised as a Read tool in the XHS-MCP MCP Server, which means it retrieves data without modifying state.
Register the XHS- MCP server in PolicyLayer and add a rule for xhs_get_recent_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-MCP. Nothing to install.
xhs_get_recent_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_get_recent_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_get_recent_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_get_recent_notes is provided by the XHS- MCP server (lastkimi/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 →