AI agents call check_placement 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 performs constraint validation and returns a result about whether a proposed action would be valid. It does not actually place or move the footprint (no Write effect), does not execute arbitrary code (no Execute effect), and does not delete or destroy data (no Destructive effect). It is a read-only check operation with no side effects, making it a Read category tool with low severity risk.
From the tool's definition Tool description states 'Check if placing/moving a footprint to (x, y) would violate constraints' — this is a validation/query operation that reads design state and constraints without modifying the design or executing external commands.
Attacks that exploit this kind of access
Check if placing/moving a footprint to (x, y) would violate constraints. 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 check_placement: 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.
check_placement 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 check_placement 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 check_placement. 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.
check_placement 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 →