Two developers ran real-world experiments using Figma's MCP with Claude Code to convert Figma designs into code. Key findings: the tool is highly literal and does exactly what you ask — no more. Specificity in prompts is critical; vague requests yield inconsistent results. Visual translation from Figma to code is accurate, but structural best practices (file separation, responsiveness, component organization) must be explicitly requested. Applying changes to an existing codebase works better than greenfield generation because Claude has structural context to follow. A major practical blocker is Figma's MCP quota on the free tier (~6 requests/month), which severely limits experimentation. Design library mapping is also a current weak point.
Table of contents
My experiment: applying design changes to an existing projectQuaresma’s experiments: starting from scratchWhat we learnedThe quota problemWhere this leaves us1 Comment
Sort: