AI agents call list_cross_sheet_nets to retrieve information from Kicad without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list' verb strongly implies data retrieval without side effects. Cross-sheet nets are design analysis data. The empty description lowers confidence slightly, but the naming pattern aligns with other read operations like 'list' commands in EDA tools. No action verbs (add, delete, execute) are present.
From the tool's definition Tool name 'list_cross_sheet_nets' indicates a read-only operation that retrieves/lists networking information across schematic sheets. No parameters suggest modification, deletion, or execution.
Attacks that exploit this kind of access
list_cross_sheet_nets. It is categorised as a Read tool in the Kicad MCP Server, which means it retrieves data without modifying state.
Register the Kicad MCP server in PolicyLayer and add a rule for list_cross_sheet_nets: 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.
list_cross_sheet_nets is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_cross_sheet_nets 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 list_cross_sheet_nets. 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.
list_cross_sheet_nets 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 →