insert_model · Melo MCP: Risk & Policy

WHAT IT DOES

What insert_model does on Melo

AI agents use insert_model to create or update resources in Melo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Melo environment.

WHY IT NEEDS A POLICY

Why insert_model needs a policy

This tool creates or adds new assets to the workspace, which is a reversible modification (the inserted model can be deleted). It does not delete, execute arbitrary code, move money, or trigger external operations beyond asset insertion.

From the tool's definition insert_model adds a new model to the Roblox workspace from the Creator Store. The description uses the verb 'Insert' and states it places a model into the workspace, creating new content that modifies the current development project.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

insert_model Rate-limited

insert_model stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "insert_model": {
      "limits": [
        {
          "counter": "insert_model_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about insert_model

What does the insert_model tool do? +

Insert a model from the Roblox Creator Store into the workspace. Args: - assetId (number): The Creator Store asset ID Returns: { name, path } of the inserted model. It is categorised as a Write tool in the Melo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on insert_model? +

Register the Melo MCP server in PolicyLayer and add a rule for insert_model: 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 Melo. Nothing to install.

What risk level is insert_model? +

insert_model is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit insert_model? +

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

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

insert_model is provided by the Melo MCP server (yannyhl/linkedsword-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.