AI agents use construct_object 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.
The name 'construct_object' suggests creating a new 3D object in Blender, which is a Write operation. The server description mentions creating objects and manipulating 3D scenes. However, the description is empty, which significantly lowers confidence. It could potentially execute scripts or destructively overwrite existing objects, but 'construct' most commonly implies creation/write.
From the tool's definition Tool name 'construct_object' and server context of creating/manipulating 3D scenes in Blender
Documented attack patterns abuse exactly the kind of access construct_object gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Blender, and nothing reaches the server without passing your rules. This is the rule we recommend for construct_object:
{
"version": "1",
"default": "deny",
"tools": {
"construct_object": {
"limits": [
{
"counter": "construct_object_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}construct_object stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
construct_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 construct_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. Nothing to install.
construct_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 construct_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 construct_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.
construct_object is provided by the Blender MCP server (sandraschi/blender-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Blender, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
77 Blender tools catalogued and risk-classified — across an index of 43,000+ MCP servers.