AI agents use set_texture to create or update resources in Blender — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Blender environment.
This tool modifies the state of a 3D scene by applying a texture to an object. While the change is reversible (textures can be removed or replaced), it does alter the scene state, making it a Write operation rather than Read. Severity is medium because misuse could deface a scene or waste resources, but effects are local to the 3D model and fully undoable.
From the tool's definition Tool applies (modifies) a texture to an object. The verb 'apply' and 'previously downloaded texture' indicate the tool changes the appearance/properties of a 3D object, which is a reversible modification operation.
Attacks that exploit this kind of access
Apply a previously downloaded Polyhaven texture to an object. It is categorised as a Write tool in the Blender MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Blender MCP server in PolicyLayer and add a rule for set_texture: 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 Blender. Nothing to install.
set_texture 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 set_texture 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 set_texture. 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.
set_texture is provided by the Blender MCP server (silwings1986/blender-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 →