AI agents use add_trace 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.
This tool creates new PCB trace segments, which is a write operation that modifies the electronic design. While traces are fundamental to PCB layout, they can be undone or modified, making this a Write rather than Destructive category. The severity is medium because an AI agent adding incorrect traces could create electrical problems, short circuits, or design defects, but these can be corrected before manufacturing.
From the tool's definition Tool name 'add_trace' and description 'Add a trace segment between two points' indicate creation of PCB trace routing, which modifies the PCB design document.
Attacks that exploit this kind of access
Add a trace segment between two points. 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 add_trace: 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.
add_trace 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_trace 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_trace. 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_trace 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 →