AI agents invoke kicad.fill_zones to trigger actions in Eda. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers a PCB layout operation (zone filling) that modifies the board state by computing and filling copper pour zones. It is an external operation with side effects on the design file, but it is reversible (zones can be unfilled or refilled), placing it in Execute rather than Write or Destructive. Misuse has medium blast radius as it could corrupt zone fills or affect downstream manufacturing outputs.
From the tool's definition Fill all zones. Must be done before DRC or Gerber export.
Attacks that exploit this kind of access
[Requires open project] Fill all zones. Must be done before DRC or Gerber export. It is categorised as a Execute tool in the Eda MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Eda MCP server in PolicyLayer and add a rule for kicad.fill_zones: 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 Eda. Nothing to install.
kicad.fill_zones is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the kicad.fill_zones 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 kicad.fill_zones. 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.
kicad.fill_zones is provided by the Eda MCP server (saeronlab/eda-mcp). 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 →