Start recording a new macro
AI agents invoke macro_start_recording 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.
Macro recording in SolidWorks enables capture of arbitrary user actions and commands that can later be executed automatically. This is a form of code execution, as recorded macros are scripts that perform operations whose effects depend entirely on what actions are recorded during the session.
From the tool's definition Start recording a new macro - directly initiates macro recording which captures and can execute arbitrary operations within SolidWorks, constituting code execution in the CAD environment.
Attacks that exploit this kind of access
Start recording a new macro. 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 macro_start_recording: 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.
macro_start_recording 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 macro_start_recording 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 macro_start_recording. 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.
macro_start_recording is provided by the Solidworks MCP server (solidworks-mcp-server). 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 →