AI agents use kicad.set_value to create or update resources in Eda — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Eda environment.
The tool creates or modifies component properties (e.g., resistor values, capacitor ratings) within a KiCad schematic/PCB design. This is a Write operation because it changes design data reversibly. The severity is medium because modifying component values could cause design errors or require rework, but changes are typically undoable within the design tool.
From the tool's definition Tool name 'set_value' and description 'Set the value property of a component' indicate modification of component parameters. This is reversible data modification within a PCB design file.
Attacks that exploit this kind of access
Set the value property of a component. Example: set_value(ref=. It is categorised as a Write tool in the Eda MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Eda MCP server in PolicyLayer and add a rule for kicad.set_value: 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.set_value 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 kicad.set_value 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.set_value. 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.set_value 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 →