AI agents use duplicate_sheet to create or update resources in Kicad — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kicad environment.
Duplicating a sheet in KiCad creates new design content (reversible via undo). While not destructive or financial, it modifies the project state and could impact design if misused by an agent (e.g., creating unwanted duplicates). Classified as Write rather than Execute because it performs a specific design operation, not arbitrary code execution.
From the tool's definition Tool name 'duplicate_sheet' indicates creation/replication of design elements. Empty description limits specificity, but context from sibling tools (add_*, add_hierarchical_sheet) and server purpose (PCB/schematic automation with read/write capabilities)…
Attacks that exploit this kind of access
duplicate_sheet. It is categorised as a Write tool in the Kicad MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kicad MCP server in PolicyLayer and add a rule for duplicate_sheet: 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 Kicad. Nothing to install.
duplicate_sheet 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 duplicate_sheet 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 duplicate_sheet. 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.
duplicate_sheet is provided by the Kicad MCP server (productofamerica/mcp-server-kicad). 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 →