// SCAN REPORT

Xiaozhi

9 tools. 6 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

6 can modify or destroy data

3 read-only

9 tools total

Community server · catalogue entry verified 03/07/2026

How to control Xiaozhi ↓

TOOL MAP

What Xiaozhi exposes to your agents

Read (3) Write / Execute (5) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Xiaozhi tools

Destructive · Medium clear_playlist This tool irreversibly removes all items from a playlist, which is a destructive action that cannot be undone through the tool itself. Execute · Low stop_music This tool executes a command that controls media playback state—stopping playback and clearing the current track. Execute · Medium calculator The tool evaluates Python expressions at runtime. Execute · Low next_song This tool triggers an external media playback operation — advancing to the next track — which is an action with real-world side effects on a running media player.

6 of Xiaozhi's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Xiaozhi

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

Deny destructive operations

{
  "clear_playlist": {
    "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

{
  "add_to_playlist": {
    "limits": [
      {
        "counter": "add_to_playlist_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_playlist": {
    "limits": [
      {
        "counter": "get_playlist_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 Xiaozhi — 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 XIAOZHI →

Instant setup, no code required.

FULL CATALOGUE

All 9 Xiaozhi tools

DESTRUCTIVE 1 tools

Destructive clear_playlist 清空播放列表。

EXECUTE 4 tools

Execute calculator For mathamatical calculation, always use this tool to calculate the result of a python expression. You can use Execute next_song 切换到播放列表中的下一首歌。 Execute previous_song 切换到播放列表中的上一首歌。 Execute stop_music 停止音乐播放并清除当前曲目。

WRITE 1 tools

Write add_to_playlist 将歌曲添加到播放列表。

READ 3 tools

Read get_playlist 获取当前播放列表中的所有歌曲。 Read resolve_music_url 解析歌曲最终直链，不直接播放。兼容 id/song_id 两种参数命名。 Read search_music_pro 搜索音乐。根据关键词搜索歌曲，返回歌曲列表。

EXPLORE

Related servers

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

FAQ

Questions about Xiaozhi

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

Yes. The Xiaozhi server exposes 1 destructive tools including clear_playlist. 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 Xiaozhi? +

The Xiaozhi server has 1 write tools including add_to_playlist. 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 Xiaozhi.

How many tools does the Xiaozhi MCP server expose? +

9 tools across 4 categories: Destructive, Execute, Read, Write. 3 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Xiaozhi? +

Register the Xiaozhi 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 Xiaozhi tool call.

Deterministic rules across all 9 Xiaozhi tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON XIAOZHI →

Instant setup, no code required.

9 Xiaozhi tools catalogued and risk-classified — across an index of 43,000+ MCP servers.