发布纯文本笔记到小红书平台,支持添加话题标签
AI agents use publish_text to create or update resources in Mcp Xhs Publisher — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Xhs Publisher environment.
This tool creates new content (text notes) on a public platform. It is reversible (posts can typically be deleted), so it falls under Write rather than Destructive. However, severity is high because an AI agent misusing this could spam the platform, post inappropriate content, or impersonate the user at scale, causing reputational damage and platform violations.
From the tool's definition Tool name 'publish_text' and description '发布纯文本笔记到小红书平台' (publish plain text notes to Xiaohongshu platform) indicate content creation and posting to a social media platform.
Attacks that exploit this kind of access
发布纯文本笔记到小红书平台,支持添加话题标签. It is categorised as a Write tool in the Mcp Xhs Publisher MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Xhs Publisher MCP server in PolicyLayer and add a rule for publish_text: 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 Mcp Xhs Publisher. Nothing to install.
publish_text 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 publish_text 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 publish_text. 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.
publish_text is provided by the Mcp Xhs Publisher MCP server (noveldig/mcp-xhs-publisher). 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 →