AI agents use lock_objects to create or update resources in GOLEM-3DMCP-Rhino- — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GOLEM-3DMCP-Rhino- environment.
Locking/unlocking objects in a CAD document is a state modification operation that is reversible and non-destructive. While it affects document state, it does not execute arbitrary operations, delete data, or create irreversible changes. This places it in the Write category. Severity is low because the impact is limited to object accessibility flags with no direct data loss or execution risk.
From the tool's definition Tool description states: "Lock or unlock objects in the Rhino document." This modifies object state (lock/unlock status) but does not delete, execute code, or create financial transactions. The operation is reversible—objects can be unlocked.
Documented attack patterns abuse exactly the kind of access lock_objects 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 lock_objects:
{
"version": "1",
"default": "deny",
"tools": {
"lock_objects": {
"limits": [
{
"counter": "lock_objects_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}lock_objects 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.
Lock or unlock objects in the Rhino document. It is categorised as a Write tool in the GOLEM-3DMCP-Rhino- MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GOLEM-3DMCP-Rhino- MCP server in PolicyLayer and add a rule for lock_objects: 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.
lock_objects 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 lock_objects 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 lock_objects. 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.
lock_objects 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.