Think inside your AI world.
PayPal through Unl
PayPal lists every open dispute with its amount and its deadline. Deciding which ones earn your attention this afternoon, and which can wait for the weekly batch, is a call you have already made once - you just haven't applied it consistently.
PayPal through Unl reads live dispute details and your rolling merchant-insights loss rate against the escalation rule you have ratified, so 'does this need a reply today?' comes back as a verdict, not a raw list, naming the condition it hasn't met.
What PayPal holds
PayPal's MCP tool catalogue includes:
- transaction history with pagination and filters
- invoice records and their status
- dispute details and evidence deadlines
- subscription plans and individual subscription status
- merchant insights and business analytics
What the naked read gives you
Ask PayPal and it hands back the full dispute queue: amount, filing date, evidence deadline, current status, alongside the subscription and transaction records tied to each case. Nothing is hidden or summarised away - every figure you'd need is there, just not ranked by what matters most today.
The frame judges the data it is given; it does not verify the source’s accuracy.
What changes when PayPal is read measured
Say you set an escalation rule after spending an entire afternoon responding to disputes that turned out to be routine: a dispute only gets a same-day reply if it's above $200 and PayPal's merchant insights show your rolling loss rate has climbed past 8 percent that week - below that, it waits for Friday's batch.
'Does this dispute need a reply today?' returns, measured: not today - the dispute is $340, which clears the amount bar, but this week's loss rate sits at 5 percent, under the 8 percent line you set before escalating becomes automatic. PayPal supplied the dispute amount and the loss-rate trend; your ratified rule supplied the escalation bar, there to protect afternoons from disputes that don't move the number.
And back again
When the loss rate later climbs past 8 percent for two weeks running, you lower the amount bar to $100 so smaller disputes start counting too. The next dispute PayPal returns is read against that tightened rule straight away.
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 decide which PayPal dispute needs a same-day reply?
Yes, through Unl. Once you have ratified an escalation rule - a dispute-value threshold, a loss-rate trigger, whatever combination fits your business - Unl reads each open dispute against it and returns a verdict: reply today, or hold for the batch, with the reason.
How do I connect PayPal to Claude?
PayPal runs both a local and a remote MCP server, with the remote endpoint at mcp.paypal.com, covering transactions, invoices, disputes, subscriptions, and merchant insights. Connected through Unl, those reads arrive measured against your ratified rules rather than handed over as a flat list.
Does Unl respond to disputes or refund money in my PayPal account?
Unl reads through PayPal, 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.