Published 10 September 2026 · Source dated 7 May 2026
Figma's Config 2026 session on agentic workflows showed teams connecting design tokens straight to code via MCP, using what it called 'hyper tokens' and reusable style fragments. Sloppy token naming is now a machine-readability problem, not just a designer-handoff one.
The same Config 2026 deep dive on Figma's MCP server covered something quieter than the agent-on-canvas headline: teams pairing design tokens with code through MCP, building reusable style fragments (framed as 'hyper tokens') so an agent — not just a developer — can pick up typography and spacing decisions correctly.
This is the practical edge of the design-systems trend: tokens were always meant to be a shared language between design and code. Now that language also has to make sense to an AI agent with no context beyond what's written in the file, which raises the bar on naming and structure.
Coach
Pick one component in your design system and check whether its token names (colour, spacing, type) are clear enough that an agent — or a new teammate — could infer their purpose without asking you.
Google's Material Design 3 popularised dynamic, token-based theming back in 2021, and it's still what most design-system setups get measured against. If you're building variables in Figma or tokens in Penpot, M3's structure is worth studying, not because it's new, but because it's proven.
open Material 3's token docs and compare their primitive-vs-role token split against your own Figma or Penpot library — note one gap you could fix this week.
Creative Market's 2026 trend forecast flags 'Glasscore' — blur, glow and translucent layers — as a rising visual style. For teams running token-based design systems, that means more theming flexibility, not just flat colour tokens.
Open your team's (or a starter) design system file and check whether blur/elevation tokens exist — if not, sketch one variant using Figma or Penpot's effect styles.
Some teams are wiring AI coding assistants into their design token workflow, using rules and MCP connections to keep components consistent. It's promising but still fragile in practice.
pick one component in your (or a practice) design system and check whether its tokens are named consistently enough that an AI tool could use them without guessing.
