AI agents use add_pcb_text 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 creates or modifies PCB design data (text annotations on silkscreen/fab layers) but does not delete, execute code, move funds, or trigger external operations with unpredictable side effects. The changes are reversible and represent normal design workflow operations.
From the tool's definition Tool name 'add_pcb_text' and description 'Add text to the PCB (silkscreen, fab layer, etc.)' indicate creation/modification of PCB design elements. The verb 'add' and action of placing text on specific layers are reversible operations typical of design tools.
Attacks that exploit this kind of access
Add text to the PCB (silkscreen, fab layer, etc.). 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 add_pcb_text: 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.
add_pcb_text 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 add_pcb_text 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 add_pcb_text. 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.
add_pcb_text 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 →