Transforming design-to-code with MCP

Transforming the Design‐to‐Code Economy at Quartex by combining Figma’s MCP server, a structured design system, and LLM augmented UI generation.

Artificial Intelligence

MCP Server

Workflows

When I joined Quartex, one of the first problems I noticed was the constant back-and-forth between designers and engineers. We’d mock up a new reporting widget in Figma, then spend days debating token names and CSS assignments. By the time code landed, it often looked nothing like the original vision. I knew there had to be a better way.

The Transaction Costs of Traditional Handoffs

In the world of enterprise software, every design-to-development handoff carries hidden overhead:
  • Translation Toll: Designers describe component intent in docs, tokens, annotations, comments; developers decode it.
  • Rework Tax: Misaligned spacing, naming conventions, and style mismatches force multiple review cycles.
  • Visibility Deficit: Once visuals leave Figma, designers sometimes loose sight of what ships, and engineers lack design context.
  • Multiple Stacks: Various teams are working with diverse stacks, compounded by inorganic growth (M&A) often seen in enterprise. Achieving a homogenised architecture and design is expensive, and often slow to progress at pace.

Even with a mature design system, the need for the developer to interpret the intent accumulates, slowing down delivery and driving up the total cost of change.

Introducing MCP as a bridge

When I discovered Figma’s Community-contributed MCP server. In my first experiment I dropped our dashboard file into the tool and watched it spit out Redux-ready React components, complete with semantic class names and tidy CSS variables. It felt like magic—almost a sci-fi moment where design and code shared the same language.

In our pilot, MCP achieved unprecidented fidelity to our visual designs. Suddenly we weren’t guessing at margins or style names. The tooling generated everything we needed, what arrived in the codebase was: Clean, Readable Markup, Correct Component Structure & Behaviour, Styling Aligned with Our Token Library, this enabled engineers could focus on logic and performance instead of manual translation. That one change reclaimed nearly 30 hours of sprint time in our first week.

In economic terms, MCP absolved the design-code dept instantly by automating the translation step.

Design System's done right are a Currency

MCP only works if you give it clear rules. We took a hard look at our design system and tightened it up. Every colour, every spacing token and every button variant now has a single, unambiguous nomenclature. Component variants live in predictable pages. We even added a simple JSON schema so the MCP server never has to guess which style to apply.

In much the same way a stable currency underpins a healthy economy, a robust design system underpins MCP’s value:
  • Semantic Tokens in our design system ensured styling consistency
  • Well-Named Component Variants removed interpretation ambiguity
  • Modular Architecture lets AI assistants snap parts together predictably
Without this structure, the MCP feed is a map without a legend, AI tools can’t discern which styles or behaviours to apply. Design systems transform raw data into actionable assets. A well curated design system is paramount to

Ideating to production level quality with Natural Language

Once our system was refined, we connected MCP output to our GPT business instance. Instead of hunting through menus or writing boilerplate, product managers can open a chat window in Storybook and say things like “Show me a three-column KPI grid with header filters and date selectors.” Within seconds they get a live preview, ready for feedback.
“Create a three-column KPI grid with a header card for ‘Active Incidents’ and footer toggles for daily, weekly, monthly views.”
This initiative frees us to think bigger. When non-designers can sketch ideas with words, we get instant clarity on requirements. We can iterate faster and avoid expensive rework later. This isn't about displacing today' conventional roles, but it certainly catalyses bluring the lines between them.

From Hand-Off to Harmony

This new workflow changes how our teams collaborate. Engineers can focus on architecture and integration. Designers can double down on interaction patterns and micro-animations. Product leads can validate features with real business metrics instead of vague requirements. MCP becomes our shared ledger of intent and outcome.

In practice that means our weekly demos now include both a visual snapshot and a small ROI snapshot of how much time we saved, or what revenue uplift we expect from a particular feature. Design is no longer a cost centre; it’s part of our growth story.

Looking Ahead, What's Next?

We built this system in a large enterprise setting with dedicated design-system resources. Leaner teams may struggle to achieve system health necessary to enable direct interpretation by LLMs and struggle with the unanimous adoption of semantic tokens across active projects. My long-term goal is to help lower the barrier to entry so that any product team can tap into this economy of design, to do that i'm I’m exploring the creation of an open-source “system starter kit” for Figma and MCP so any product team can adopt these ideas instantly.

We're close to a reality where an individual can viably spin up a shared design-to-code pipeline as easily as they install a dependency. That’s the future I see, where the only limit on innovation is our imagination, not the overhead of handoff.

Final Thoughts

The handoff friction between design and code is dissolving at pace. By combining a strict design system with MCP and natural-language UI generation, we can collapse misinterpretation, enable autonomous visual ideation, and drive value like never seen before.
I’m excited to keep pushing these ideas forward, and I’d love to chat about how you can adopt them into your organisations workflow.

Explore more

Let’s Build Tomorrow’s Products

Foster strategic collaboration to design AI-native systems that amplify human capabilities and experience