AI agents invoke zoom_selected 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.
This tool drives a UI/viewport action in Rhino 8 (zooming the camera to selected objects), which constitutes triggering an external operation in a running application. It does not merely read data but actively changes the state of the viewport. No data is created, modified, or destroyed, but it executes an external application command, placing it in Execute rather than Read.
From the tool's definition 'Zoom to show specific objects in a viewport' — triggers a viewport action in Rhino, an external application operation
Documented attack patterns abuse exactly the kind of access zoom_selected 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 zoom_selected:
{
"version": "1",
"default": "deny",
"tools": {
"zoom_selected": {
"limits": [
{
"counter": "zoom_selected_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}zoom_selected 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.
Zoom to show specific objects in a viewport. 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 zoom_selected: 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.
zoom_selected 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 zoom_selected 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 zoom_selected. 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.
zoom_selected 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.