action_perform · Live2d To Agent MCP: Risk & Policy

WHAT IT DOES

What action_perform does on Live2d To Agent

AI agents invoke action_perform to trigger actions in Live2d To Agent. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why action_perform needs a policy

This tool triggers playback of animations/actions on a Live2D desktop pet, which constitutes executing an external operation (driving a UI/visual element). It has no destructive, financial, or persistent write effects. Severity is low as the blast radius is limited to controlling a desktop pet's animations. Confidence is slightly reduced because the description is truncated and available actions are not listed.

From the tool's definition 播放 Live2D 角色的语义动作 (Play semantic actions for Live2D character)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

action_perform Rate-limited

action_perform stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "action_perform": {
      "limits": [
        {
          "counter": "action_perform_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Live2d To Agent, so you can run agents against it safely.

FAQ

Questions about action_perform

What does the action_perform tool do? +

播放 Live2D 角色的语义动作。可用动作：. It is categorised as a Execute tool in the Live2d To Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on action_perform? +

Register the Live2d To Agent MCP server in PolicyLayer and add a rule for action_perform: 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 Live2d To Agent. Nothing to install.

What risk level is action_perform? +

action_perform is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit action_perform? +

Yes. Add a rate_limit block to the action_perform 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 action_perform completely? +

Set action: deny in the PolicyLayer policy for action_perform. 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 action_perform? +

action_perform is provided by the Live2d To Agent MCP server (lmy414/live2d-to-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.