发布小红书内容
AI agents use xiaohongshu_publish to create or update resources in Xiaohongshu MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xiaohongshu MCP Server environment.
This tool creates and publishes new content to a social media platform, which is a reversible write operation. It creates posts that can later be edited or deleted, but does not irreversibly destroy data. Severity is high because publishing automated content at scale could constitute spam, defacement, or platform ToS violations, and could damage the account holder's reputation.
From the tool's definition Tool name is 'xiaohongshu_publish' and description states '发布小红书内容' (publish Xiaohongshu content). Server description confirms it 'supports publishing text content with images to Xiaohongshu accounts.'
Attacks that exploit this kind of access
发布小红书内容. It is categorised as a Write tool in the Xiaohongshu MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xiaohongshu MCP Server MCP server in PolicyLayer and add a rule for xiaohongshu_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 MCP Server. Nothing to install.
xiaohongshu_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 xiaohongshu_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 xiaohongshu_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.
xiaohongshu_publish is provided by the Xiaohongshu MCP Server MCP server (muhenan/xiaohongshu-mcp-python). 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 →