AI agents use save_drawing 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 or modifies files on disk by persisting CAD drawings to DWG format. It is Write rather than Destructive because: (1) saving typically overwrites only if explicitly directed to an existing file, and (2) the operation is reversible (files can be deleted or replaced).
From the tool's definition Tool name 'save_drawing' with description indicating it saves/persists drawings to file system (with optional file_path parameter). Description translates to 'Save drawing. Parameters: file_path? (can be empty, use default output path)'.
Attacks that exploit this kind of access
保存图纸。参数: file_path?(可为空,使用默认输出路径). 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 save_drawing: 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.
save_drawing 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 save_drawing 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 save_drawing. 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.
save_drawing 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 →