Fudge MCP
Give your AI agents design taste from existing websites
170 followers
Give your AI agents design taste from existing websites
170 followers
Meet Fudge: a design reference engine for AI agents. Instead of asking AI to make another “modern, premium” interface from scratch, let it search nearly 10,000 real websites by fonts, colors, components, layouts, page types, and visual similarity. Fudge combines measured design evidence with screenshots, runs locally through MCP, and remembers references you save with its Chrome extension. Give your coding agent better taste and not more adjectives.
Free Options
Launch Team / Built With
really like this framing of "taste" as something extractable rather than just scraping colors and fonts. what happens when the source site is inconsistent, like a company mid-rebrand where half the pages still use the old design system - does it pick up on the dominant pattern and ignore the outliers, or does it get confused and blend both into something that matches neither
PageBot
@omri_ben_shoham1 That's really up to the model, fudge is mostly a database, how the agent decides to use it is up to your instructions
the part I'd want to be careful with is how close "measured design evidence" gets to a specific real company's actual brand identity versus generic patterns. pulling fonts/colors/layout from a category of sites as inspiration is fine, but if the agent leans hard on one particular close visual match, the output could end up looking like a clone of that specific brand rather than "good taste" in general. is there anything nudging toward blending multiple references instead of over-indexing on the single best match
The bit I like is it hands the agent measured design evidence — actual fonts, colors, spacing — instead of another screenshot to eyeball, plus the Chrome extension to save references as I browse. My day-one workflow question: does that saved-reference library live locally with the MCP or sync to a Fudge account, and when I'm on one project can I point my agent at just my saved set instead of searching the full 10k every time?
"Better taste and not more adjectives" is painfully accurate. We spend a lot of time on moodboards for client design work, and we're actively integrating AI generation into that workflow right now — so searching real sites by fonts/components/layouts instead of prompting "cleaner, more premium" for the fifth time is exactly the missing piece. Definitely trying this one.
In case it comes across a similarly designed website for referencing purposes, will it take the risk of copying fonts and structures that may have copyrights or trademarks associated with the respective brand or does it restrict itself from using the styles altogether?
Really interesting MCP use case.
I'm curious whether design context becomes a standard capability every AI agent will need, or if it's mainly valuable for creative workflows.
honestly love the idea of giving agents actual references instead of vibes, that part is really smart. one thing though, it would be super helpful if you could filter by industry or specific site categories, like only e-commerce or only SaaS landing pages, so the results are way more targeted when you're working on a particular project.