Published 27 August 2026 · Source dated 10 July 2025
MCP standardises how AI tools read context straight from your design files — Figma's Dev Mode MCP Server lets Copilot, Cursor and Claude Code pull components directly. A year on, this is now baseline expectation, not a demo.
MCP (Model Context Protocol) standardises how AI tools pull context from design files — Figma's Dev Mode MCP Server lets Copilot, Cursor, Windsurf and Claude Code read your components directly instead of guessing from screenshots. A good while after this first shipped, it's now **established**: teams building design systems treat MCP support as table stakes, not a novelty demo.
The catch nobody advertises: MCP tools are only as good as your naming and structure. Messy layers and untokenised styles give an agent nothing useful to read, no matter how good the model is.
Coach
Open your design system's component library and check if tokens and layers are named clearly — that's exactly what MCP-based tools read first, so tidy naming pays off twice.
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.
