AI agents use set_trace_width 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 modifies PCB design parameters (trace width) without deleting data. Changes to trace width can be undone/revised in KiCad, making it Write rather than Destructive. Medium severity reflects potential for design errors affecting circuit functionality, but blast radius is limited to the current project design.
From the tool's definition Tool name 'set_trace_width' indicates modification of PCB trace properties. Description is empty, but sibling tools like 'add_copper_zone', 'add_pcb_line', and 'add_pcb_text' all perform write operations on KiCad PCB designs.
Attacks that exploit this kind of access
set_trace_width. 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 set_trace_width: 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.
set_trace_width 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 set_trace_width 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 set_trace_width. 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.
set_trace_width 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 →