Check model geometry for errors
AI agents call check_geometry to retrieve information from Solidworks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only analysis of model geometry to identify errors. It retrieves and evaluates data about the model's geometric properties but does not modify, create, delete, or execute any external operations. This is consistent with Read category tools that perform inspection and validation without side effects.
From the tool's definition Tool is named 'check_geometry' and described as 'Check model geometry for errors' - this is a diagnostic/validation operation that queries and inspects existing model data without modifying, deleting, or executing external code.
Attacks that exploit this kind of access
Check model geometry for errors. It is categorised as a Read tool in the Solidworks MCP Server, which means it retrieves data without modifying state.
Register the Solidworks MCP server in PolicyLayer and add a rule for check_geometry: 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.
check_geometry is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the check_geometry 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 check_geometry. 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.
check_geometry 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 →