AI agents invoke kicad.run_erc 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.
ERC (Electrical Rules Check) is a standard KiCad operation that runs a validation/analysis pass over the schematic. The 'run_' prefix indicates execution of an automated check. It reads design data and produces a report but does not modify data, so it is Execute rather than Write or Read. Description is empty, lowering confidence. No financial or destructive implications expected.
From the tool's definition Tool name: kicad.run_erc — the 'run_' prefix strongly suggests executing a process (Electrical Rules Check in KiCad EDA context).
Attacks that exploit this kind of access
kicad.run_erc. 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.run_erc: 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.run_erc 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.run_erc 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.run_erc. 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.run_erc 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 →