AI agents invoke hollow_mesh_model to trigger actions in Kiln. 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.
Based on the name, this tool likely modifies a 3D mesh model by hollowing it out, which would be a Write or Execute operation (modifying geometry data). Given the context of a 3D printing AI control server with tools like 'add_mesh_chamfer' and 'add_mesh_fillet' (similar mesh modification siblings), this is likely an Execute-level operation that transforms mesh geometry.
From the tool's definition Tool name 'hollow_mesh_model' suggests a mesh modification operation; description is empty and uninformative.
Attacks that exploit this kind of access
hollow_mesh_model. It is categorised as a Execute tool in the Kiln MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kiln MCP server in PolicyLayer and add a rule for hollow_mesh_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 Kiln. Nothing to install.
hollow_mesh_model 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 hollow_mesh_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_mesh_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_mesh_model is provided by the Kiln MCP server (codeofaxel/Kiln). 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 →