Scale objects in two dimensions (planar scale preserving the third axis).
AI agents invoke scale_objects_2d to trigger actions in GOLEM-3DMCP-Rhino-. 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.
Scaling objects is a geometric transformation that modifies the model state irreversibly in practical terms (scaling cannot be easily undone without user intervention). However, it does not delete or overwrite data (Destructive), nor does it create new data permanently (Write). It executes a transformation operation whose effects are state-dependent and would require explicit undo actions.
From the tool's definition Tool performs 'scale_objects_2d' which modifies geometry in Rhino 8. The server description explicitly states it 'give[s] AI agents direct, programmatic control of Rhino 8 — create geometry, run booleans, drive Grasshopper, capture viewports, and execute…
Documented attack patterns abuse exactly the kind of access scale_objects_2d gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GOLEM-3DMCP-Rhino-, and nothing reaches the server without passing your rules. This is the rule we recommend for scale_objects_2d:
{
"version": "1",
"default": "deny",
"tools": {
"scale_objects_2d": {
"limits": [
{
"counter": "scale_objects_2d_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}scale_objects_2d 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.
Scale objects in two dimensions (planar scale preserving the third axis). It is categorised as a Execute tool in the GOLEM-3DMCP-Rhino- MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GOLEM-3DMCP-Rhino- MCP server in PolicyLayer and add a rule for scale_objects_2d: 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 GOLEM-3DMCP-Rhino-. Nothing to install.
scale_objects_2d 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 scale_objects_2d 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 scale_objects_2d. 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.
scale_objects_2d is provided by the GOLEM-3DMCP-Rhino- MCP server (thekinghippopotamus/golem-3dmcp-rhino-). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GOLEM-3DMCP-Rhino-, 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.
89 GOLEM-3DMCP-Rhino- tools catalogued and risk-classified — across an index of 43,000+ MCP servers.