AI agents use xhs_create_or_update_post to create or update resources in XHS-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your XHS-MCP environment.
This tool creates new notes or modifies existing drafts, which are reversible write operations. The severity is medium because misuse could result in unwanted draft content being queued, but the impact is limited since: (1) the content hasn't been published yet, (2) drafts can presumably be deleted before posting, and (3) the actual publication requires a separate 'post' command.
From the tool's definition Tool description states '创建或更新待发布的笔记文件,添加到发布队列' (create or update draft notes, add to publishing queue). The verbs 'create' and 'update' indicate data modification.
Attacks that exploit this kind of access
创建或更新待发布的笔记文件,添加到发布队列。创建后的笔记可以通过 post 命令发布到小红书。. It is categorised as a Write tool in the XHS-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the XHS- MCP server in PolicyLayer and add a rule for xhs_create_or_update_post: 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_create_or_update_post 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_create_or_update_post 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_create_or_update_post. 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_create_or_update_post 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 →