Hollow the specified models to reduce material usage.
AI agents use hollow_model to create or update resources in Formlabs Local — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Formlabs Local environment.
This tool modifies existing model data (hollowing geometry) which is a reversible write operation on the model within the scene. It does not delete or destroy the model entirely, but it does alter its structure. Since the change could potentially be undone by re-importing the original model, it falls under Write rather than Destructive. Misuse could corrupt a model intended for printing, giving it medium severity.
From the tool's definition 'Hollow the specified models to reduce material usage' — modifies the geometry of a 3D model by hollowing it out
Attacks that exploit this kind of access
Hollow the specified models to reduce material usage. It is categorised as a Write tool in the Formlabs Local MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Formlabs Local MCP server in PolicyLayer and add a rule for hollow_model: 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 Formlabs Local. Nothing to install.
hollow_model 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 hollow_model 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 hollow_model. 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.
hollow_model is provided by the Formlabs Local MCP server (mkebiclioglu/formlabs-local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →