Rhino connects to an AI assistant through the Model Context Protocol (MCP) with the native 
RhinoMCP
and 
mcpstart
commands. Once connected, you can describe the massing or form you’re after in plain language, watch the assistant build and adjust it live in your Rhino session, and refine it by continuing the conversation instead of driving every modeling tool by hand. In this tutorial, we’ll use that conversation to vibe-model an architectural concept from a rough massing study to a refined form.
What You’ll Need
- Rhino 9 for Windows or Mac.
- An MCP-capable AI chat client, such as Claude Desktop, that can connect to a local MCP server.
- No scripting knowledge required. The assistant drives Rhino’s modeling tools for you; this tutorial focuses on directing form, not writing code.
Connect Rhino to an AI Assistant
NOTE TO SELF: Reuse/link the connection steps from Vibe Coding your Tools in Rhino once that section is finalized, instead of duplicating it here.
mcpstart
again to close the bridge, or quit the chat client, once you’re done experimenting.Describe the Massing in Conversation
NOTE TO SELF: Walk through describing an architectural massing study (e.g. a site volume or building block) to the assistant and watching it build a first-pass form live in the viewport.
Refine the Form Conversationally
NOTE TO SELF: Cover iterating on massing, proportions, and site context purely through conversation, the same way vibe-coding/everyday-tools iterates on the speaker grid script.
Where to Go from Here
- See Rhino in Architecture for the broader set of Rhino modeling guides for architecture.
- Remember to close the mcpstart
bridge when you’re not actively using it — there’s no reason to leave an AI assistant with live code execution access to Rhino running in the background.
