Published 5 September 2026 · Source dated 1 September 2026
Figma's MCP server exposes your actual components and tokens to connected AI agents, meaning generated screens and code are only as on-brand as your library is well-organised. Sloppy naming or orphaned styles now show up directly in AI output.
The practical effect of agent-and-MCP tooling landing in design systems: your library's hygiene is no longer just an internal nuisance, it's the source material an AI reads before generating anything. Untokenised colours, duplicate components, and vague naming all get inherited by whatever the agent produces. Teams with clean, well-documented systems are seeing genuinely usable output; teams without are seeing confident-looking nonsense. This is adoption-stage: real teams are testing it against real libraries right now, and the gap between tidy and messy systems is becoming visible fast, not theoretical.
Coach
pick your messiest Figma or Penpot component, rename its layers and variants properly, and note the before/after for your portfolio.
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.
