AI agents use export_footprint_svg 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.
Exporting data to a file format is a write operation—it creates new data in SVG format. However, it is reversible (the SVG can be deleted or overwritten), causes no destructive changes to the underlying KiCad project, and does not execute arbitrary code or move data of financial value. The blast radius is minimal, as an AI misuse would only result in unwanted SVG exports, which are harmless outputs. Severity is low.
From the tool's definition The tool name 'export_footprint_svg' and description 'Export footprint to SVG' indicate it creates/generates a new SVG file output from existing KiCad footprint data. This is a write operation that produces a new file artifact.
Attacks that exploit this kind of access
Export footprint to SVG. 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 export_footprint_svg: 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.
export_footprint_svg 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 export_footprint_svg 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 export_footprint_svg. 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.
export_footprint_svg 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 →