Run an agent CAD design loop over one or more attempt scripts: review each attempt with review_cad, continue past functional attempts that still have unresolved review warnings, return structured repair prompts, and optionally write a Studio-compatible build record JSON for visual replay.
Risk signalsAccepts file system path (attempts[].file) · Accepts freeform code/query input (attempts[].code) · High parameter count (29 properties)
Part of the Kernelcad server.
Free to start. No card required.
AI agents invoke design_loop to trigger processes or run actions in Kernelcad. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
design_loop can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"design_loop": {
"limits": [
{
"counter": "design_loop_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Kernelcad policy for all 48 tools.
These attack patterns abuse exactly the kind of access design_loop gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Run an agent CAD design loop over one or more attempt scripts: review each attempt with review_cad, continue past functional attempts that still have unresolved review warnings, return structured repair prompts, and optionally write a Studio-compatible build record JSON for visual replay.. It is categorised as a Execute tool in the Kernelcad MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kernelcad MCP server in PolicyLayer and add a rule for design_loop: 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 Kernelcad. Nothing to install.
design_loop 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 design_loop 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 design_loop. 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.
design_loop is provided by the Kernelcad MCP server (kernelcad). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 48 Kernelcad tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.