AI agents use set_component_property 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.
The tool modifies component properties reversibly—properties can be changed back to previous values or deleted. While it affects PCB/schematic design state, the changes are not destructive (no data deletion) and not financially consequential.
From the tool's definition Tool description states 'Set any property on a placed component. Creates it if missing.' This is a create/modify operation on component properties, characteristic of Write category.
Attacks that exploit this kind of access
Set any property on a placed component. Creates it if missing. 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_component_property: 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_component_property 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_component_property 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_component_property. 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_component_property 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 →