Published 31 August 2026 · Source dated 30 August 2026
Some Figma MCP servers now sync design tokens to code and back again automatically, which sounds great until you ask who's checking the diff. Worth trying, not worth trusting blindly yet.
Among the newer entries in a Figma MCP server comparison is a tool that pulls design tokens from Figma, generates shadcn/ui React components from saved specs, then pushes token updates back into Figma — a two-way pipeline between design system and codebase. It's listed as 'Steady' with commits as recent as 15 days ago, so it's actively maintained, but it's also young: this pattern hasn't been through many real design system audits yet, and token drift bugs are exactly the kind of thing that's hard to spot until production.
If your team runs a token-based system in Figma or Penpot, this is the direction things are heading — just not the thing to plug into your only source of truth yet.
Coach
if you maintain a token library, read how the sync works before you touch it — try it on a throwaway file first, not your live design system.
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.
