Add text at a specified position in AutoCAD
AI agents use draw_text to create or update resources in AutoCAD MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AutoCAD MCP Server environment.
The tool creates new text objects in a CAD drawing, which is a Write operation—data is added/modified but not deleted and can be undone. Severity is medium because misuse could add unwanted content to a CAD project, but the effect is reversible through standard undo/delete operations.
From the tool's definition Tool name 'draw_text' and description 'Add text at a specified position in AutoCAD' indicate creation of new content within a CAD document. This is a reversible modification operation.
Attacks that exploit this kind of access
Add text at a specified position in AutoCAD. It is categorised as a Write tool in the AutoCAD MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AutoCAD MCP Server 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 AutoCAD MCP Server. 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 AutoCAD MCP Server MCP server (porta048/autocad-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 →