AI agents use move_footprint 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.
Moving a footprint modifies the PCB design state but does not destroy data or trigger external operations. It is reversible and similar to other sibling tools like 'add_pcb_line' and 'add_pcb_text' that create or modify design elements. The blast radius is medium because misplacement could require design rework, but the action itself is not irreversible or destructive.
From the tool's definition Tool name 'move_footprint' and description 'Move a footprint to a new position' indicate modification of PCB layout data. This is reversible—the footprint can be moved back to its original position or to another location.
Attacks that exploit this kind of access
Move a footprint to a new position. 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 move_footprint: 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.
move_footprint 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 move_footprint 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 move_footprint. 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.
move_footprint 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 →