model_load · Live2d To Agent MCP: Risk & Policy

WHAT IT DOES

What model_load does on Live2d To Agent

AI agents invoke model_load 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 model_load needs a policy

Loading a model from a filesystem path triggers an external operation with side effects (loading files into memory, changing the active model state). It is not a simple read, but it also doesn't destructively delete data. The ability to specify an arbitrary directory path could be misused to load unintended files, raising the severity to medium.

From the tool's definition 加载 Live2D 模型。指定包含 .model3.json 的目录路径 — triggers an external operation to load a model from a specified directory path

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

model_load Rate-limited

model_load 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": {
    "model_load": {
      "limits": [
        {
          "counter": "model_load_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 model_load

What does the model_load tool do? +

加载 Live2D 模型。指定包含 .model3.json 的目录路径，. 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 model_load? +

Register the Live2d To Agent MCP server in PolicyLayer and add a rule for model_load: 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 model_load? +

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

Can I rate-limit model_load? +

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

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

model_load 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.