AI agents use retexture_create to create or update resources in Meshy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Meshy environment.
This tool modifies an existing 3D model by applying new textures, which is a write operation. It creates a new textured variant of a model without permanently deleting or destroying the original. The severity is medium because misuse could generate unwanted textured models and consume API quota, but effects are reversible.
From the tool's definition Tool name 'retexture_create' and description 'Apply new textures to a 3D model' indicate creation/modification of model data. The action is reversible (textures can be re-applied or reverted), not destructive.
Attacks that exploit this kind of access
Apply new textures to a 3D model. Provide either input_task_id or model_url, and either text_style_prompt or image_style_url. It is categorised as a Write tool in the Meshy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Meshy MCP server in PolicyLayer and add a rule for retexture_create: 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. Nothing to install.
retexture_create 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_create 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_create. 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_create is provided by the Meshy MCP server (meshy-mcp-server). 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 →