Insert a surfaceFromBoundary([c1, c2, c3, c4], opts?) declaration into the user's .kcad.ts immediately before the last top-level return. Fills the interior of 4 boundary Curve3D refs with a single NURBS face via OCCT BRepOffsetAPI_MakeFilling — the canonical Coons-patch primitive. The 4 curves wa...
Risk signalsAccepts freeform code/query input (code)
Part of the Kernelcad server.
Free to start. No card required.
AI agents use add_surface_from_boundary to create or modify resources in Kernelcad. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call add_surface_from_boundary repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Kernelcad.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"add_surface_from_boundary": {
"limits": [
{
"counter": "add_surface_from_boundary_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Kernelcad policy for all 48 tools.
These attack patterns abuse exactly the kind of access add_surface_from_boundary gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Insert a surfaceFromBoundary([c1, c2, c3, c4], opts?) declaration into the user's .kcad.ts immediately before the last top-level return. Fills the interior of 4 boundary Curve3D refs with a single NURBS face via OCCT BRepOffsetAPI_MakeFilling — the canonical Coons-patch primitive. The 4 curves walk an ordered loop: curve_bindings[0] = bottom, [1] = right, [2] = top, [3] = left; adjacent endpoints must coincide within 1e-6 mm or capture emits feature.surface-from-boundary.corner-mismatch. The result has type Surface — chain .thicken(t) or .toShape() via add_feature on the returned binding name. opts.continuity accepts a single grade ('C0' | 'C1' | 'C2') applied to all 4 edges or a length-4 array per edge; defaults to 'C0'. opts.sampling controls NbPtsOnCur (default 15). Validates every curve_bindings[i] is declared in the source via regex before inserting (fast structured error vs capture-time stack). Returns the modified code + diagnostics. Side-effect-free.. It is categorised as a Write tool in the Kernelcad MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kernelcad MCP server in PolicyLayer and add a rule for add_surface_from_boundary: 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.
add_surface_from_boundary 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 add_surface_from_boundary 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 add_surface_from_boundary. 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.
add_surface_from_boundary 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.