AI agents invoke execute_blender_code to trigger actions in Bonsai-mcp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool allows execution of arbitrary Python code within Blender's runtime environment. Arbitrary code execution is inherently in the Execute category and warrants critical severity because: (1) an AI agent could execute malicious code with full Blender privileges, (2) it could read/write/delete files on the host system, (3) it could trigger external operations or network requests, (4) the blast radius is maximal…
From the tool's definition Tool name is 'execute_blender_code' and description states 'Execute arbitrary Python code in Blender.' The word 'arbitrary' indicates unrestricted code execution capability.
Documented attack patterns abuse exactly the kind of access execute_blender_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bonsai-mcp, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_blender_code:
{
"version": "1",
"default": "deny",
"tools": {
"execute_blender_code": {
"limits": [
{
"counter": "execute_blender_code_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_blender_code stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute arbitrary Python code in Blender. It is categorised as a Execute tool in the Bonsai-mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Bonsai- MCP server in PolicyLayer and add a rule for execute_blender_code: 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 Bonsai-mcp. Nothing to install.
execute_blender_code is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_blender_code 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 execute_blender_code. 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.
execute_blender_code is provided by the Bonsai- MCP server (jotaderodriguez/bonsai_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Bonsai-mcp, 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.
17 Bonsai-mcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.