AI agents use flatten_hierarchy 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.
The tool name suggests restructuring a hierarchical design by flattening it—a reversible modification of project structure. This aligns with the Write category (modifies data reversibly) rather than Execute or Destructive, as flattening can typically be undone via version control or undo.
From the tool's definition Tool name 'flatten_hierarchy' with sibling tools that perform structural modifications (add_hierarchical_sheet, add_hierarchical_label) on KiCad projects; context indicates write/modify operations on schematics and PCBs.
Attacks that exploit this kind of access
flatten_hierarchy. 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 flatten_hierarchy: 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.
flatten_hierarchy 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 flatten_hierarchy 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 flatten_hierarchy. 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.
flatten_hierarchy 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 →