// SCAN REPORT

Xhs Kit

16 tools. 10 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 30 Jun 2026

10 can modify or destroy data

6 read-only

16 tools total

Community server · catalogue entry verified 30/06/2026

How to control Xhs Kit ↓

TOOL MAP

What Xhs Kit exposes to your agents

Read (6) Write / Execute (9) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Xhs Kit tools

Destructive · Medium delete_cookies This tool irreversibly deletes the cookies file and resets the login state. Execute · High login_with_browser This tool triggers an external browser automation action (opening a browser window for QR code scanning and authentication). Write · Medium debug_publish_content Although framed as a debug/validation tool that does not actually publish, it is intrinsically linked to the publish_content operation and interacts with content creation systems. Write · Medium favorite_feed This tool creates or modifies user state by adding or removing notes from a user's favorites collection.

10 of Xhs Kit's 16 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Xhs Kit

PolicyLayer is an MCP gateway — it sits between your AI agents and Xhs Kit, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_cookies": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "debug_publish_content": {
    "limits": [
      {
        "counter": "debug_publish_content_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_login_status": {
    "limits": [
      {
        "counter": "check_login_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Xhs Kit — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON XHS KIT →

Instant setup, no code required.

FULL CATALOGUE

All 16 Xhs Kit tools

DESTRUCTIVE 1 tools

Destructive delete_cookies 删除 cookies 文件，重置登录状态。删除后需要重新登录。

EXECUTE 1 tools

Execute login_with_browser 浏览器扫码登录（会弹出浏览器窗口）。

WRITE 8 tools

Write debug_publish_content Debug 模式：验证发布内容而不实际发布 Write favorite_feed 收藏或取消收藏笔记 Write like_feed 点赞或取消点赞笔记 Write post_comment 发表评论到笔记 Write publish_content 发布小红书图文内容 Write publish_text_card 发布文字配图笔记（将文字生成为卡片图片） Write publish_with_video 发布小红书视频内容（仅支持本地单个视频文件） Write reply_comment 回复笔记下的指定评论

READ 6 tools

Read check_login_status 检查小红书登录状态（只检查 cookies 文件是否存在） Read get_feed_detail get_feed_detail Read get_login_qrcode 获取登录二维码（返回 Base64 图片）。 Read get_user_profile 获取用户主页信息 Read list_feeds 获取首页推荐列表 Read search_feeds 搜索小红书内容

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Xhs Kit

Can an AI agent delete data through the Xhs Kit MCP server? +

Yes. The Xhs Kit server exposes 1 destructive tools including delete_cookies. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Xhs Kit? +

The Xhs Kit server has 8 write tools including debug_publish_content, favorite_feed, like_feed. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Xhs Kit.

How many tools does the Xhs Kit MCP server expose? +

16 tools across 3 categories: Destructive, Read, Write. 6 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Xhs Kit? +

Register the Xhs Kit MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Xhs Kit tool call.

Deterministic rules across all 16 Xhs Kit tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON XHS KIT →

Instant setup, no code required.

16 Xhs Kit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.