Re-texture an existing model into a new variant. Identify the source by
AI agents use retexture_model to create or update resources in Meshy Bottube — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Meshy Bottube environment.
The tool modifies an existing 3D model by applying new textures, creating a new variant. This is a reversible modification (write/create operation) rather than destructive, as the original model is not deleted. The description is truncated, slightly lowering confidence, but 're-texture into a new variant' clearly implies a write/create action.
From the tool's definition Re-texture an existing model into a new variant
Attacks that exploit this kind of access
Re-texture an existing model into a new variant. Identify the source by. It is categorised as a Write tool in the Meshy Bottube MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Meshy Bottube MCP server in PolicyLayer and add a rule for retexture_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 Meshy Bottube. Nothing to install.
retexture_model is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the retexture_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.
Set action: deny in the PolicyLayer policy for retexture_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.
retexture_model is provided by the Meshy Bottube MCP server (scottcjn/meshy-bottube-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →