AI agents use no_connect_pin 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.
This tool modifies schematic design data by adding a no-connect flag to a pin. This is a reversible Write operation (the flag can be removed or modified). It does not delete data (Destructive), execute arbitrary code (Execute), move money (Financial), or merely read data (Read). The impact is localized to a single component pin annotation, making severity medium rather than high.
From the tool's definition Tool places a no-connect flag on a component pin, which modifies the schematic state. The description explicitly indicates an action that creates/adds a marking ('Place a no-connect flag') on the design, changing the schematic structure reversibly.
Attacks that exploit this kind of access
Place a no-connect flag on a component pin. 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 no_connect_pin: 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.
no_connect_pin 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 no_connect_pin 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 no_connect_pin. 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.
no_connect_pin 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 →