AI agents call validate_hierarchy to retrieve information from Kicad without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates a validation function, which by nature examines and reports on the state of hierarchical schematic structures without changing them. The empty description reduces confidence slightly, but the semantic meaning of 'validate' strongly implies a non-destructive, non-modifying check. No sibling tools suggest destructive operations on hierarchy itself, further supporting Read classification.
From the tool's definition Tool name 'validate_hierarchy' suggests a validation/checking operation. KiCad hierarchy typically refers to schematic sheet organization. Validation is inherently a read-only operation that inspects but does not modify data.
Attacks that exploit this kind of access
validate_hierarchy. It is categorised as a Read tool in the Kicad MCP Server, which means it retrieves data without modifying state.
Register the Kicad MCP server in PolicyLayer and add a rule for validate_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.
validate_hierarchy is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the validate_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 validate_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.
validate_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 →