modify_object
AI agents use modify_object to create or update resources in Blender MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Blender MCP environment.
The name 'modify_object' strongly implies modifying an existing 3D object in Blender (e.g., changing position, scale, material, etc.), which is a reversible Write operation. However, the description is empty, lowering confidence. It sits alongside 'delete_object' and 'execute_python' which are more severe, and 'create_object' which is Write — 'modify_object' most plausibly fits Write.
From the tool's definition Tool name 'modify_object' on a server that enables control of Blender 3D for 'object creation, modification, deletion, and Python script execution'
Attacks that exploit this kind of access
modify_object. It is categorised as a Write tool in the Blender MCP 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 modify_object: 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 MCP. Nothing to install.
modify_object 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 modify_object 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 modify_object. 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.
modify_object is provided by the Blender MCP server (nowcika/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 →