AI agents invoke run_drc to trigger actions in Kicad. 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.
The tool triggers execution of KiCad's DRC analysis engine, which is a diagnostic operation that reads the PCB state and produces a report. It performs computation/analysis but does not create, modify, delete, or irreversibly change the PCB design. No side effects occur beyond generating validation output.
From the tool's definition Tool name 'run_drc' and description 'Run Design Rules Check (DRC) on a PCB' indicate execution of a built-in KiCad validation operation that analyzes design quality without modifying or deleting the PCB.
Attacks that exploit this kind of access
Run Design Rules Check (DRC) on a PCB. It is categorised as a Execute tool in the Kicad MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kicad MCP server in PolicyLayer and add a rule for run_drc: 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.
run_drc 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 run_drc 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 run_drc. 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.
run_drc 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 →