@penpot/mcp
Bridges design and development workflows by enabling Claude to interact with Penpot designs programmatically, reducing handoff friction and design-to-code tr…
Penpot's official MCP server. It lets an LLM query, transform, and create design elements in a Penpot design file by executing code against the Penpot Plugin API. Runs as a local MCP server plus a companion Penpot MCP Plugin that connects over WebSocket, enabling design-to-code and code-to-design workflows.
- Ask Claude to extract design specifications from Penpot files for development handoff
- Generate component code based on Penpot design assets and layout information
- Automate documentation of UI dimensions, colors, and typography from design files
Bridges design and development workflows by enabling Claude to interact with Penpot designs programmatically, reducing handoff friction and design-to-code translation errors.
Engineering teams using Penpot for design systems who need to automate design asset extraction and specification generation.
https://www.npmjs.com/package/@penpot/mcp
By alotor
How to Get It
npx -y @penpot/mcp@latest
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Extract design specifications from Penpot files for development handoff
Trust Signals Auto-scanned
Data & Access
Community Pulse Active
Discussed on Hacker News
- Show HN: Penpot MCP Server — Hacker News · 2 pts
1 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 48,882 GitHub stars; contributors unknown; last commit 0d ago; license MPL-2.0.
Things to check
- Setup has three moving parts: run the MCP server, run the plugin web server, and connect the plugin inside Penpot. The LLM writes and executes arbitrary code in the Penpot plugin environment — review its actions on files you care about. Match the package version to your Penpot version (@latest for the current release, @beta for the test instance).
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 48,882 GitHub stars; contributors unknown; last commit 0d ago; license MPL-2.0.