Apply a previously downloaded Polyhaven texture to an object.
AI agents use set_texture to create or update resources in BlenderMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your BlenderMCP environment.
This is a Write operation because it modifies scene data by applying a texture to an object—a reversible change. It doesn't execute arbitrary code, delete data, or cause financial impact. Severity is medium because misuse could corrupt scene aesthetics or apply inappropriate textures, but the effect is reversible and limited to visual properties.
From the tool's definition Tool applies/modifies a texture on an object ("Apply a previously downloaded Polyhaven texture to an object"), which changes object properties in the Blender scene.
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 BlenderMCP 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 BlenderMCP. 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 (ujs204/claude-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 →