Published 6 September 2026 · Source dated 5 June 2025
Figma's Dev Mode MCP server (beta) feeds your file's components and variables straight to AI coding tools, so generated code matches your design system. It's live now on Dev/Full seats — Penpot has no equivalent yet.
Figma's Dev Mode MCP server (in beta) lets AI coding tools like Cursor or Claude pull directly from your Figma file — components, variables, styles — so generated code actually matches your design system instead of guessing at hex codes. It's available on any Dev or Full seat. Why it matters for design-systems thinking: if your components and variables are messy, the AI-generated code will be messy too — MCP just makes that gap obvious faster. This is a good forcing function to actually tidy up your token structure rather than leaving it as a 'someday' task. Penpot doesn't ship an equivalent MCP server yet, so if you're comparing tools for a future role, this is a real capability gap worth knowing about.
Coach
open one component in Dev Mode, check whether its variables and styles are named clearly enough that a stranger (or an AI) could use them correctly — tidy up one if not.
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.
