Medium Risk

meshy_retexture

Apply new AI-generated textures to an existing 3D model using Meshy AI. IMPORTANT: Before calling this tool, ask the user to provide EITHER: - text_style_prompt: A text description of the desired texture style (e.g.

How to control meshy_retexture ↓

What meshy_retexture does on Meshy MCP Server

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

Medium Risk

Why meshy_retexture needs a policy

This tool modifies an existing 3D model by applying new textures to it. It creates/modifies data (texture application) but is reversible in principle — the original model still exists and a new textured version is created. This fits the Write category. Misuse could waste API credits or apply unintended textures, but the blast radius is moderate.

From the tool's definition Apply new AI-generated textures to an existing 3D model

Documented attack patterns abuse exactly the kind of access meshy_retexture gives an agent:

How to control meshy_retexture

PolicyLayer is an MCP gateway — it sits between your AI agents and Meshy MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for meshy_retexture:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "meshy_retexture": {
      "limits": [
        {
          "counter": "meshy_retexture_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

meshy_retexture 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.

  1. Create a free account and register Meshy MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about meshy_retexture

What does the meshy_retexture tool do? +

Apply new AI-generated textures to an existing 3D model using Meshy AI. IMPORTANT: Before calling this tool, ask the user to provide EITHER: - text_style_prompt: A text description of the desired texture style (e.g. It is categorised as a Write tool in the Meshy MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on meshy_retexture? +

Register the Meshy MCP Server MCP server in PolicyLayer and add a rule for meshy_retexture: 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 Meshy MCP Server. Nothing to install.

What risk level is meshy_retexture? +

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

Can I rate-limit meshy_retexture? +

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

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

meshy_retexture is provided by the Meshy MCP Server MCP server (meshy-dev/meshy-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Meshy MCP Server tool call.

Start from Meshy MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

20 Meshy MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.