Add raw OpenSCAD code directly for complex shapes not covered by other tools
AI agents invoke custom_scad to trigger actions in 3D MCP Server. 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 accepts and runs arbitrary user-supplied OpenSCAD code, which constitutes code execution. While OpenSCAD itself is a geometry scripting language (not a general OS shell), it can invoke external processes or file system operations depending on the OpenSCAD build and configuration.
From the tool's definition Add raw OpenSCAD code directly — allows arbitrary OpenSCAD script execution without restriction
Attacks that exploit this kind of access
Add raw OpenSCAD code directly for complex shapes not covered by other tools. It is categorised as a Execute tool in the 3D MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the 3D MCP Server MCP server in PolicyLayer and add a rule for custom_scad: 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 3D MCP Server. Nothing to install.
custom_scad 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 custom_scad 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 custom_scad. 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.
custom_scad is provided by the 3D MCP Server MCP server (jagjerez-org/3d-mcp-server). 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 →