Published 4 September 2026 · Source dated 2 September 2026
As AI agents start reading design systems directly through MCP-style integrations, teams are cleaning up token naming and documentation so agents (and humans) don't misread intent. It's a quieter but real shift in design-system hygiene.
Design system teams tracking MCP and agent integrations are noticing the same pain point: agents are only as good as the structure they're fed. Vague token names, undocumented component variants and inconsistent naming that a human designer could mentally patch over now break agent workflows outright.
The practical response showing up across design-systems coverage is a renewed push on token hygiene — clear naming conventions, documented intent, and structured component metadata — treating the design system as something both people and machines need to parse reliably.
This isn't a flashy trend; it's an adoption-stage discipline shift, driven by teams already running agents against their libraries and hitting friction.
Coach
pick one component in your Figma or Penpot library and rename its tokens as if an agent (not a person) had to understand them cold.
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.
