AI agents use blender_export 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 tool most likely exports Blender scene data to files (e.g., .blend, .fbx, .obj, .gltf formats), which is a Write operation—it creates/serializes data artifacts. While export doesn't modify source data, it produces new files/outputs.
From the tool's definition Tool name 'blender_export' suggests exporting/writing Blender project data to files. The server description indicates it allows users to 'create, manipulate, and automate 3D scenes' and the sibling tools like 'blender_batch' and 'blender_api_docs' context…
Documented attack patterns abuse exactly the kind of access blender_export 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 blender_export:
{
"version": "1",
"default": "deny",
"tools": {
"blender_export": {
"limits": [
{
"counter": "blender_export_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}blender_export 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.
blender_export. 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 blender_export: 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.
blender_export 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 blender_export 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 blender_export. 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.
blender_export 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.