AI agents use kicad.annotate_schematic 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.
This tool creates or modifies schematic data (reference designators) in a reversible manner. While it changes the design, the changes can be undone via undo functionality in KiCad or re-annotation. It does not execute external code, delete data, move money, or trigger irreversible operations.
From the tool's definition Tool performs auto-assignment of reference designators to components, which modifies the schematic document by adding annotation metadata to unannotated components. The description states it will 'auto-assign' and modify component properties.
Attacks that exploit this kind of access
Auto-assign reference designators to all unannotated components. 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.annotate_schematic: 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.annotate_schematic 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.annotate_schematic 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.annotate_schematic. 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.annotate_schematic 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 →