like_feed · Xhs Kit MCP: Risk & Policy

WHAT IT DOES

What like_feed does on Xhs Kit

AI agents use like_feed to create or update resources in Xhs Kit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xhs Kit environment.

WHY IT NEEDS A POLICY

Why like_feed needs a policy

This tool creates or modifies social interactions (likes) on the Xiaohongshu platform. While the action is reversible (you can unlike content), it constitutes a write operation that changes platform state. The blast radius is medium because unauthorized liking could spam the platform, manipulate engagement metrics, or impersonate user preferences at scale, though financial or destructive consequences are unlikely.

From the tool's definition like_feed description: '点赞或取消点赞笔记' (like or unlike a note). The verb '点赞' (like/upvote) modifies social platform state; it creates or removes a like interaction, which is reversible.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

like_feed Rate-limited

like_feed stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "like_feed": {
      "limits": [
        {
          "counter": "like_feed_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Xhs Kit, so you can run agents against it safely.

FAQ

Questions about like_feed

What does the like_feed tool do? +

点赞或取消点赞笔记. It is categorised as a Write tool in the Xhs Kit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on like_feed? +

Register the Xhs Kit MCP server in PolicyLayer and add a rule for like_feed: 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 Kit. Nothing to install.

What risk level is like_feed? +

like_feed is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit like_feed? +

Yes. Add a rate_limit block to the like_feed 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.

How do I block like_feed completely? +

Set action: deny in the PolicyLayer policy for like_feed. 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.

What MCP server provides like_feed? +

like_feed is provided by the Xhs Kit MCP server (luweizheng/xhs-kit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.