AI agents are now reading your design tokens directly
Published 16 September 2026 · Source dated 11 September 2026
MCP servers built for design tools increasingly let coding agents pull tokens straight out of Figma/Penpot files to generate code, so loose token naming now breaks AI output too, not just human handoff. Design system teams are starting to treat token hygiene as an AI-readiness problem, not just a documentation nicety.
- Several MCP server implementations for design tools now list "pull tokens, generate code" as a core feature rather than a plugin add-on.
- If your token names are inconsistent or your component variants are messy, an agent will happily generate broken or inconsistent code straight from them.
- That raises the bar for governance: naming conventions and documentation aren't just nice-to-have anymore — they're becoming machine-readable requirements.
- Worth flagging: this tooling is new and reliability varies a lot between different MCP server implementations, so don't assume it's solved.
Coach
Audit one component in your Figma or Penpot library — rename any vague token (like "blue2") to something a machine, and a new teammate, could understand 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.
