Create a new sketch on a specified plane or face
AI agents use create_sketch 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.
The tool creates new geometry (a sketch) in the SolidWorks model, which is a reversible write operation. While sketches are fundamental to CAD design, creating them modifies the model structure and can affect downstream operations. This is more severe than a simple read (which would just query existing data) but less severe than destructive operations (delete, purge) or financial transactions.
From the tool's definition Tool creates a new sketch on a specified plane or face; this is a reversible creation operation that modifies the CAD model state.
Attacks that exploit this kind of access
Create a new sketch on a specified plane or face. 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 create_sketch: 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.
create_sketch 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 create_sketch 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 create_sketch. 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.
create_sketch 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 →