Think inside your AI world.

Braze through Unl

Braze's MCP will read back a canvas's lift over holdout on request. Unl asks first whether that lift still clears the bar you ratified for keeping the canvas in rotation.

Braze through Unl reads canvas and campaign analytics against the retention lift you have ratified, so 'is this canvas still earning its slot?' comes back renew-or-retire with the condition it hasn't met.

What Braze holds

What Braze's MCP genuinely hands back, read-only:

  • Canvas analytics - step-by-step performance and lift over holdout for a given canvas.
  • Campaign analytics - aggregated send performance for a specific campaign.
  • Segment detail - the audience definition and size behind a given segment.
  • Custom attributes - the attribute schema available for targeting or reporting.
  • Content and template detail - email templates and content blocks tied to a send.

What the naked read gives you

Ask Braze's MCP how a retention canvas is performing and it answers cleanly - lift over holdout, step completion, current and aggregated, no PII involved. The server does not obscure the numbers or make you request access twice; the read is genuinely there for the asking. The analytics say nothing about the 3-point lift your team fixed, the dividing line between a canvas that has earned its calendar slot and one that has simply always been there.

The frame judges the data it is given; it does not verify the source’s accuracy.

What changes when Braze is read measured

A CRM manager ratified the rule in Unl: a retention canvas has to lift 7-day return rate by at least 3 percentage points over the holdout group to keep its slot in the send calendar, because a slot given to a flat canvas is a slot not given to a new test.

'Is this canvas still earning its slot?' returns, measured: retire - the canvas is showing a 0.8-point lift over holdout, under the ratified 3-point bar. Braze supplied the canvas analytics; your ratified rule supplied the lift threshold that turns a modest number into a decision to make room.

And back again

Once the retire call is made, Unl keeps the lift figure and the 3-point bar it missed attached to this canvas rather than letting the reasoning disappear with the chat, so the next planning cycle, when someone asks why this canvas is no longer in rotation, finds the renew-or-retire call and the holdout number that produced it already on record.

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

Would the verdict change if the canvas is redesigned and lift improves?

Yes. The 3-point bar stays fixed; what moves is the lift figure Braze reports after the redesign runs against a fresh holdout. If the rebuilt canvas clears 3 points, the same question returns renew, not retire.

How do I connect Braze to Claude?

Braze offers a remote, OAuth-based MCP server alongside its earlier local beta; add it as a custom connector in Claude following Braze's own setup guide, scoping the API key to the non-PII endpoints you want it to read, and Unl reads through that connection.

Does Unl send messages or change canvases in Braze?

Unl reads through Braze, and can write back on your explicit gesture — it never acts as a side effect of a read.

What this is

Think inside your AI world — you stay in command

Unlimitless (Unl to friends) holds what you've settled, reads what your tools are showing, and catches what's changed out in the world — and hands your AI whatever bears on the work, the moment it's needed, without you asking. The right thing, in front of the model, unprompted, with you in command of the call. So you keep moving toward what you set out to build, on top of everything you've already decided.

It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector. Quick to connect, in a couple of steps.

Unlimitless is open now to invited Alpha. Apply for the Beta waitlist to come in ahead of the full launch:

Alpha is invite-only · free at launch.