AI agents use draw_text 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.
The tool creates new text elements in a CAD drawing, which modifies the design state reversibly. While it doesn't execute arbitrary code or delete data, it does persistently alter the CAD document. This is a Write operation because the changes are reversible (text can be edited or removed) and non-destructive.
From the tool's definition Tool name 'draw_text' with description indicating it 'adds text' (添加文本) to CAD drawings with parameters for position, text content, and optional formatting. This is a creation operation on design data.
Attacks that exploit this kind of access
添加文本。参数: position, text, height?, rotation?, 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 draw_text: 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_text 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_text 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_text. 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_text 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 →