refine_model · Tripo AI MCP Server MCP: Risk & Policy

WHAT IT DOES

What refine_model does on Tripo AI MCP Server

AI agents invoke refine_model to trigger actions in Tripo AI MCP Server. 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 refine_model needs a policy

This tool triggers an external AI processing operation on the Tripo3D API — it executes a refinement pipeline on an existing 3D model. It doesn't merely read data, nor does it destructively delete anything. It runs a computational task on an external service whose output depends on the input task ID, placing it in the Execute category.

From the tool's definition Refine a draft 3D model to improve its quality. Use the task ID from a previous text_to_3d or image_to_3d task.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

refine_model Rate-limited

refine_model 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": {
    "refine_model": {
      "limits": [
        {
          "counter": "refine_model_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 Tripo AI MCP Server, so you can run agents against it safely.

FAQ

Questions about refine_model

What does the refine_model tool do? +

Refine a draft 3D model to improve its quality. Use the task ID from a previous text_to_3d or image_to_3d task. It is categorised as a Execute tool in the Tripo AI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on refine_model? +

Register the Tripo AI MCP Server MCP server in PolicyLayer and add a rule for refine_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 Tripo AI MCP Server. Nothing to install.

What risk level is refine_model? +

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

Can I rate-limit refine_model? +

Yes. Add a rate_limit block to the refine_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 refine_model completely? +

Set action: deny in the PolicyLayer policy for refine_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 refine_model? +

refine_model is provided by the Tripo AI MCP Server MCP server (pasie15/tripo-ai-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.