AI agents use add_dimension 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.
This tool creates new CAD entities (dimensions) within a drawing document, which is a reversible modification. It does not execute arbitrary code, delete data, or move money. The blast radius is medium because incorrect dimensions could corrupt design intent, but the operation can be undone/edited in CAD software.
From the tool's definition Tool adds (adds) a linear dimension annotation to CAD drawings. The name 'add_dimension' and description '添加线性标注' (add linear dimension) indicate creation of new drawing elements.
Attacks that exploit this kind of access
添加线性标注。参数: start_point, end_point, text_position?, textheight?, layer?, color?. 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 add_dimension: 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.
add_dimension 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 add_dimension 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 add_dimension. 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.
add_dimension 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 →