• 6 min read Workflow,Tools,AI Share onTwitter,LinkedIn About The Author Designer, dev, editor, writer, and nomad.More about Daniel ↬ Email Newsletter Weekly tips on front-end & UX.Trusted by 182,000+ folks. • This article has been kindly supported by our dear friends atPenpot, whose mission is to provide an open-source and open-standards platform to bring collaboration between designers and developers to the next level.Thank you! • Imagine that your Penpot file contains a full icon set in addition to the design itself, which uses some but not all of those icons. • If you were to ask an AI such as Claude or Gemini to export only the icons that are being used, it wouldn’t be able to do that. • It’s not able to interact with Penpot files. • However, aPenpot MCP servercan.
Article Summaries:
- Penpot, the open‑source design platform, is testing MCP (Machine‑Controlled Protocol) servers to enable AI assistants to interact securely with its files. The MCP server translates natural‑language AI requests into structured API calls, allowing tasks such as exporting only the icons actually used in a design. Because Penpot’s data is open‑source and API‑driven, the MCP server can perform a limited set of operations under defined permissions, bridging the gap between AI intent and file manipulation. The system includes a Python SDK, REST API, plugin and CLI tools, and supports any MCP‑enabled AI (e.g., Claude). Early demos show design‑to‑code workflows and other automated editing tasks, highlighting a more granular, privacy‑preserving approach than typical “describe‑generate” models.
Sources: