Save the scene as an OpenSCAD .scad file
AI agents use save_scad to create or update resources in 3D MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 3D MCP Server environment.
This tool performs a write operation that creates or modifies a .scad file in the filesystem. While it is reversible (files can be deleted or overwritten), it has medium severity because an AI agent could fill disk space, overwrite important design files, or create files with malicious OpenSCAD code that could harm downstream users who open/process them.
From the tool's definition Tool description states it 'Save[s] the scene as an OpenSCAD .scad file', which creates or writes a file to storage.
Attacks that exploit this kind of access
Save the scene as an OpenSCAD .scad file. It is categorised as a Write tool in the 3D MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the 3D MCP Server MCP server in PolicyLayer and add a rule for save_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.
save_scad 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 save_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 save_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.
save_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 →