Remove a component by reference designator.
AI agents call remove_component to permanently remove resources in Kicad — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a component from an electronic design is a destructive action that permanently deletes design data. While KiCad may support undo/redo in the GUI, an MCP tool that removes components represents an irreversible modification from the tool's perspective.
From the tool's definition Tool name is 'remove_component' with description 'Remove a component by reference designator.' The verb 'remove' indicates deletion of a component from a KiCad schematic or PCB design, which is an irreversible operation that cannot be undone programmatically.
Attacks that exploit this kind of access
Remove a component by reference designator. It is categorised as a Destructive tool in the Kicad MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kicad MCP server in PolicyLayer and add a rule for remove_component: 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.
remove_component is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_component 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 remove_component. 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.
remove_component 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 →