Published 9 September 2026 · Source dated 4 September 2026
As AI agents increasingly read Figma files through MCP, messy naming and unbound tokens are becoming a real blocker. Design systems are quietly being pushed to get more legible - for agents as much as humans.
More teams are letting AI agents read Figma files via MCP - but agents can only follow a system that's actually legible. Vague layer names and hardcoded values (instead of bound tokens) give agents bad context and worse output.
- This is quietly pushing teams to tighten naming conventions and document component rules more explicitly than before.
- "Agent-readable" is becoming a design-system quality bar alongside accessibility and consistency.
- It's a decent excuse to finally clean up that half-finished token library.
Coach
audit one component in your Figma or Penpot library this week - rename anything vague like 'Frame 42' and check its tokens are bound, not hardcoded.
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.
