Think inside your AI world.
Figma through Unl
Figma shows the design faithfully. Whether it honours the principles you settled on is your call — and the canvas doesn’t hold your principles.
Figma through Unl reads your live design — files, frames, components and design data — against the product principles you have ratified, so a design comes back honours-them-or-not with the principle it breaks named.
What Figma holds
Figma’s MCP server exposes the design surface:
- Files and frames
- Components and variables
- Design data and tokens
What the naked read gives you
A naked read returns the design structure. Accurate, and it won’t flag that a new screen reuses a one-off button instead of the system component, because “reuse the system” is your principle, not a Figma rule.
The frame judges the data it is given; it does not verify the source’s accuracy.
What changes when Figma is read measured
Say you’ve ratified two product principles: text contrast never below the accessibility floor, and new screens reuse system components rather than one-offs.
“Does this design hold to our principles?” returns, measured: not fully — the CTA text falls under your contrast floor, and two elements are one-offs where a system component exists, both breaching the principles you set to keep the product accessible and consistent. Figma supplied the design; your ratified principles supplied the checks and the reasons.
And back again
When you grant a deliberate exception for a marketing screen and record it, the next design read treats that screen’s one-off as allowed rather than a breach.
The answer comes back measured against what you already decided, and why.
The lane is live and open to this tool today: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.
Questions people ask
Can AI check a Figma design against our product principles?
Yes, through Unl. You ratify the principles (a contrast floor, component reuse, and why), and the live design is measured against them — the answer names which principle a design breaks, if any.
How do I connect Figma to Claude?
Figma offers an MCP server exposing files, components and design data. Through Unl the same design arrives measured against your ratified principles, so review reads as holds-or-drifts.
Does Unl change my Figma files?
Unl reads through Figma, and can write back on your explicit gesture — it never acts as a side effect of a read.
What if a screen uses a component that was detached and then edited?
Then it reads as a one-off, because that is what it now is. Figma can tell you whether a layer is still an instance of a system component; a detached copy that happens to look right has left the system, and the rule you set was about reuse rather than resemblance. The read names the screen, and whether the edit was justified stays yours.
What this is
Think inside your AI world — you stay in command
Save the thoughts, decisions and targets worth keeping, each with its reasoning, carried into every AI session the moment they matter. A new unit of exchange between you and your AI: the Settled Why with standing that travels. Unprompted.
Your whole AI world. What you decided at the epicentre. It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector — quick to connect, in a couple of steps.
MCP native·Human settled·Model agnostic·Your data
Measured Context
Connect Unl to bring the right information into the moment.
Your sources, read against the criteria you set.
The full product, open. Free at launch.