AI agents use draw_rectangle to create or update resources in CAD-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CAD-MCP environment.
Drawing rectangles creates or modifies CAD designs reversibly—the shapes can be undone/deleted later. This is a Write operation rather than Execute because it performs a specific, predictable drawing action rather than executing arbitrary commands or code. While the sibling tool 'process_command' might be Execute, this tool has a defined, limited purpose.
From the tool's definition Tool draws rectangles in CAD software by creating new geometric objects. The parameters (corner1, corner2, layer, color, lineweight) specify shape properties to be created.
Attacks that exploit this kind of access
绘制矩形。参数: corner1, corner2, layer?, color?, lineweight?. It is categorised as a Write tool in the CAD-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CAD- MCP server in PolicyLayer and add a rule for draw_rectangle: 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 CAD-MCP. Nothing to install.
draw_rectangle 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 draw_rectangle 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 draw_rectangle. 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.
draw_rectangle is provided by the CAD- MCP server (piexl/cad-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 →