保存当前活动文档。
AI agents use sw_save to create or update resources in Solidworks — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Solidworks environment.
This tool writes/modifies data by saving document state to disk. While reversible (previous versions may exist), it commits changes to the active document and could overwrite unsaved work or corrupt designs if invoked at an inappropriate time. It is not destructive (data is preserved, not deleted) and not execute-level (no arbitrary code execution).
From the tool's definition Tool name 'sw_save' and description '保存当前活动文档' (saves the current active document) indicate a file write operation that modifies and persists data in SolidWorks documents.
Attacks that exploit this kind of access
保存当前活动文档。. It is categorised as a Write tool in the Solidworks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Solidworks MCP server in PolicyLayer and add a rule for sw_save: 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 Solidworks. Nothing to install.
sw_save 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 sw_save 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 sw_save. 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.
sw_save is provided by the Solidworks MCP server (yimu0824/solidworks-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 →