Workshops - Grasshopper MCP: Use Murmurate To Turn Grasshopper Definitions Into AI Tools
Convert the Grasshopper definitions you've spent years building into tools an AI assistant can call. Learn to wrap an existing definition as a named MCP tool, declare its inputs and outputs, and run it from your LLM client in plain language.
What you'll learn
Use MCP (the Model Context Protocol) with Grasshopper and Rhino without abandoning the definitions you've built over years. With Murmurate, our Rhino and Grasshopper plugin, you'll convert a real definition into a tool an AI assistant can find and run: wrap the logic in an AI tool component, declare the inputs and outputs that matter, publish it to your tool library, and call it from your preferred LLM client in plain language. There is no configuration file, terminal, API key or code to write, and authoring never leaves the Grasshopper canvas. Murmurate is in public beta for Rhino 8 and Rhino 9 on Windows, so you can install it before the session. You'll also learn what MCP is and why it matters for computational designers, how a tool is structured so an assistant knows how to run it, how results come back into Rhino and Grasshopper, and how to test, refine and deploy responsibly.
What you'll cover
- What MCP is and why it matters for designers
- An introduction to Murmurate, our Rhino and Grasshopper plugin
- Anatomy of a tool: typed inputs, outputs and the descriptions an assistant reads
- Wrapping an existing definition as a callable tool, without leaving Grasshopper
- Publishing to a tool library and connecting an LLM client (Claude Desktop, Claude Code or any MCP client)
- Data and geometry exchange, testing and limits
Who it's for
Experienced Grasshopper users new to MCP and LLM tooling.
How the day runs
- 1
Understand MCP
What the Model Context Protocol is, why it matters for computational designers, and where Murmurate, our Rhino and Grasshopper plugin, fits in.
- 2
Anatomy of a tool
The inputs, outputs and — crucially — the descriptions that tell the LLM what a tool does and how to call it.
- 3
Prepare a definition
Take a real Grasshopper definition and expose only the inputs and outputs you care about, ready to wrap.
- 4
Wire it up
Turn the definition into a working MCP tool and register it with an MCP server.
- 5
Connect an LLM
Point the LLM client of your choosing at the server and call the definition by describing what you want.
- 6
Exchange, test & deploy
Handle data and geometry exchange between the LLM and Rhino/Grasshopper, then test, refine and deploy responsibly.
A look inside
1 day · Live online · Max 14 places
£379 + VAT
per person
- Live, instructor-led — never pre-recorded
- Certificate of attendance
- 90 days' step-by-step guide access
Date or time zone not right? Tell us below and be first to hear about new cohorts.
More workshops
Not what you're looking for? Browse the full programme — live workshops, free guides and applied-AI training.
Common Questions - Workshop FAQs
Answers to the questions we hear most from attendees.
Booking for a team, or planning something bespoke? See the full workshop FAQ
Workshop Enquiries - Questions, or Can't Make These Dates?
Tell us what's in the way — an unanswered question, a team booking, or a session time that doesn't work in your time zone. We'll come back within one business day, and you'll be first to hear when new Grasshopper MCP dates are scheduled.
Just want the next date? and we'll email you as soon as it's announced.