MCP's 'Resources' idea could reshape design systems
Published 28 August 2026 · Source dated 25 November 2024
The Model Context Protocol, launched by Anthropic in November 2024, is built around exposing structured 'resources' to AI — the same logic now underpinning how design tools let agents read components, tokens and styles.
MCP's core idea is simple: instead of every AI tool reinventing how it connects to data, you expose things as standard 'resources' an agent can read (and sometimes 'tools' it can act with). A database might expose tables as resources; a design file could expose components, colour tokens or type styles the same way. This is exactly the pattern showing up as design tools start letting AI agents read design system data directly off the canvas.
MCP itself is established — it launched in late 2024 and is now supported across every major AI client. What's still forming is how well individual tools implement it for actual design system data, so treat vendor-specific claims with a healthy dose of 'show me,' not 'trust me.'
Coach
Open your team's design system and list the five values (colours, spacing, type styles, component names) you'd expose first if an AI agent could only read a handful of 'resources.'
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.
