强制重建当前文档。
AI agents invoke sw_rebuild to trigger actions in Solidworks. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool forces a rebuild/regeneration operation in SolidWorks, which executes a computational process on the active document. It is not a simple read, nor does it delete data, but it triggers an external operation (COM automation call) that recalculates and updates the model state. Misuse could corrupt a document's feature tree or cause unintended geometry changes, hence medium severity.
From the tool's definition '强制重建当前文档' (Force rebuild the current document) — triggers an external operation in SolidWorks via COM automation
Attacks that exploit this kind of access
强制重建当前文档。. It is categorised as a Execute tool in the Solidworks MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Solidworks MCP server in PolicyLayer and add a rule for sw_rebuild: 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_rebuild is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sw_rebuild 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_rebuild. 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_rebuild 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 →