// SCAN REPORT

Live2d To Agent

11 tools. 7 can modify or destroy data without limits.

7 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

7 can modify or destroy data

4 read-only

11 tools total

Community server · catalogue entry verified 02/07/2026

How to control Live2d To Agent ↓

TOOL MAP

What Live2d To Agent exposes to your agents

Read (4) Write / Execute (7) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Live2d To Agent tools

Execute · Low expression_set This tool triggers an external operation on the Live2D desktop pet application — changing the character's displayed expression. Execute · Low action_perform This tool triggers playback of animations/actions on a Live2D desktop pet, which constitutes executing an external operation (driving a UI/visual element). Execute · Low live2d_expression This tool triggers an external operation on a running Live2D application, changing its displayed expression. Execute · Low live2d_motion This tool triggers playback of a Live2D motion/animation group on an external application.

7 of Live2d To Agent's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Live2d To Agent

PolicyLayer is an MCP gateway — it sits between your AI agents and Live2d To Agent, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "settings_set": {
    "limits": [
      {
        "counter": "settings_set_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "action_list": {
    "limits": [
      {
        "counter": "action_list_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 Live2d To Agent — 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 LIVE2D TO AGENT →

Instant setup, no code required.

FULL CATALOGUE

All 11 Live2d To Agent tools

EXECUTE 6 tools

Execute action_perform 播放 Live2D 角色的语义动作。可用动作： Execute expression_set 切换 Live2D 角色的表情。根据对话情绪选择合适的表情。 Execute live2d_expression 切换 Live2D 表情。从模型定义的表情中选择。 Execute live2d_motion 播放 Live2D 动作组。从模型定义的动作组中选择。 Execute live2d_parameter 直接操控 Live2D 底层参数。参数 ID 因模型而异，通过 live2d_status 获取可用参数。 Execute model_load 加载 Live2D 模型。指定包含 .model3.json 的目录路径，

WRITE 1 tools

Write settings_set 修改桌面宠物设置。可修改：window.width(200-600)、window.height(260-800)、

READ 4 tools

Read action_list 列出所有可用的语义动作。所有模型通用，不依赖特定 .motion3.json。 Read expression_list 列出当前模型的所有可用表情及其描述。需先执行 model_load。 Read live2d_status 获取 Live2D 状态：模型名称、可用表情、动作组、动画列表、参数组信息 Read settings_get 获取 Live2D 桌面宠物的所有当前设置：窗口大小、位置、透明度、模型缩放、偏移等。

FAQ

Questions about Live2d To Agent

How do I prevent bulk modifications through Live2d To Agent? +

The Live2d To Agent server has 1 write tools including settings_set. 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 Live2d To Agent.

How many tools does the Live2d To Agent MCP server expose? +

11 tools across 2 categories: Read, Write. 4 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Live2d To Agent? +

Register the Live2d To Agent 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 Live2d To Agent tool call.

Deterministic rules across all 11 Live2d To Agent tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LIVE2D TO AGENT →

Instant setup, no code required.

11 Live2d To Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.