Syntax-check OpenSCAD code without performing a full render. Runs OpenSCAD with output directed to /dev/null (NUL on Windows) so it only parses and evaluates the code without generating geometry output. Much faster than a full render. Captures and categorizes ECHO, WARNING, ERROR, and DEPRECATED ...
AI agents invoke validate_scad to trigger actions in OpenSCAD 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 executes an external process (OpenSCAD binary) to parse and evaluate code. While it doesn't produce geometry output, it still runs arbitrary OpenSCAD code through an external program, which constitutes executing an external operation. A malicious actor could potentially abuse the 'variables' parameter or scad_content to trigger unintended behavior in the OpenSCAD runtime.
From the tool's definition Runs OpenSCAD with output directed to /dev/null... only parses and evaluates the code without generating geometry output... Captures and categorizes ECHO, WARNING, ERROR, and DEPRECATED messages from stderr.
Documented attack patterns abuse exactly the kind of access validate_scad 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 validate_scad:
{
"version": "1",
"default": "deny",
"tools": {
"validate_scad": {
"limits": [
{
"counter": "validate_scad_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}validate_scad stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Syntax-check OpenSCAD code without performing a full render. Runs OpenSCAD with output directed to /dev/null (NUL on Windows) so it only parses and evaluates the code without generating geometry output. Much faster than a full render. Captures and categorizes ECHO, WARNING, ERROR, and DEPRECATED messages from stderr. Args: scad_content: OpenSCAD code to validate (mutually exclusive with scad_file) scad_file: Path to OpenSCAD file to validate (mutually exclusive with scad_content) variables: Variables to pass to OpenSCAD via -D flags include_paths: Additional include paths for OpenSCAD via -I flags ctx: MCP context for logging Returns: Dict with success status, valid flag, errors list, warnings list, echo_output list, and deprecated list. It is categorised as a Execute tool in the OpenSCAD MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenSCAD MCP Server MCP server in PolicyLayer and add a rule for validate_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 OpenSCAD MCP Server. Nothing to install.
validate_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 validate_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 validate_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.
validate_scad 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.