发布小红书图文笔记(需登录创作者平台)
AI agents use xhs_publish to create or update resources in Xiaohongshu — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xiaohongshu environment.
This tool creates new content on the Xiaohongshu platform, which is a reversible action (published notes can be deleted). It does not delete data (Destructive), does not transfer money (Financial), and does not execute arbitrary code (Execute).
From the tool's definition Tool name 'xhs_publish' and description '发布小红书图文笔记' (publish Xiaohongshu notes) directly performs content creation. The description indicates it 'requires login to creator platform' but does not specify restrictions on content scope or moderation bypasses.
Attacks that exploit this kind of access
发布小红书图文笔记(需登录创作者平台). It is categorised as a Write tool in the Xiaohongshu MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xiaohongshu MCP server in PolicyLayer and add a rule for xhs_publish: 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_publish is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the xhs_publish 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_publish. 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_publish 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 →