Create a new OpenSCAD model file. Args: name: File name for the model (alphanumeric, hyphens, underscores; .scad extension added automatically if missing) content: OpenSCAD source code for the model workspace: Directory to save the model in. Defaults to the configured temp_dir/models directory. c...
AI agents use create_model to create or update resources in OpenSCAD MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OpenSCAD MCP Server environment.
The tool writes new data (OpenSCAD model files) to the filesystem in a designated workspace directory. This is a classic Write operation: it creates or modifies data reversibly. While it accepts arbitrary OpenSCAD code as input, the code itself is not executed by this tool—it is merely stored as file content. There is no destructive potential (files can be deleted), no financial impact, and no direct code execution.
From the tool's definition Tool creates a new OpenSCAD model file with user-provided source code and name. Description explicitly states 'Create a new OpenSCAD model file' and returns 'success status, path, and name of the created file'. This is a reversible file creation operation.
Documented attack patterns abuse exactly the kind of access create_model gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenSCAD MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_model:
{
"version": "1",
"default": "deny",
"tools": {
"create_model": {
"limits": [
{
"counter": "create_model_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_model 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.
Create a new OpenSCAD model file. Args: name: File name for the model (alphanumeric, hyphens, underscores; .scad extension added automatically if missing) content: OpenSCAD source code for the model workspace: Directory to save the model in. Defaults to the configured temp_dir/models directory. ctx: MCP context for logging Returns: Dict with success status, path, and name of the created file. It is categorised as a Write tool in the OpenSCAD MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenSCAD MCP Server MCP server in PolicyLayer and add a rule for create_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 OpenSCAD MCP Server. Nothing to install.
create_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 create_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 create_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.
create_model is provided by the OpenSCAD MCP Server MCP server (quellant/openscad-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 OpenSCAD MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 OpenSCAD MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.