Think inside your AI world.
Paddle through Unl
Paddle's API MCP server hands an agent the transaction. Unl hands it the bar your finance function actually closes the month against.
Paddle through Unl reads transaction and report data against the reconciliation rule you have ratified, so 'is this transaction reconciled?' comes back reconcile-or-flag with the mismatch it's still carrying.
What Paddle holds
Naked, the MCP server returns whatever the transaction ledger contains. Measured, that same transaction is checked against the reconciliation rule the finance controller actually ratified:
- List transactions and get a single transaction by ID
- Get the invoice attached to a transaction
- List subscriptions and get a single subscription by ID
- List reports and get a report by ID, including CSV export
What the naked read gives you
Ask Paddle's API MCP server whether a transaction is reconciled, and it returns what the ledger holds: transaction status, the invoice tied to it, the subscription behind it, the report line it should sit inside. Complete and current, because that is the read surface Paddle built for an assistant to query - not a verdict on whether the numbers actually tie out to your books.
The frame judges the data it is given; it does not verify the source’s accuracy.
What changes when Paddle is read measured
The finance controller ratified the reconciliation rule: a transaction only counts as reconciled once its invoice has been generated, its status reads completed, and its amount matches the corresponding report line, because unmatched transactions were closing the month with a gap nobody could trace back.
'Is this transaction reconciled?' returns, measured: flag, the report line understates the transaction by four pounds, because a silent mismatch at month-end is the one that costs the most to chase later. Paddle supplied the transaction and report data; your ratified rule supplied the reconciliation bar.
And back again
The flag travels with the numbers that raised it. Unl holds the transaction, the report line and the mismatch together against the rule that compared them, so anyone re-checking that transaction later starts from the discrepancy already found instead of running the comparison over again.
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
What happens once the mismatch is corrected?
Unl re-runs the comparison against the same ratified rule once the report line is corrected. If the amounts now match and the invoice and status both check out, the verdict moves from flag to reconciled, with the original discrepancy kept on record.
How do I connect Paddle to Claude?
Install the official Paddle API MCP server and connect it to Claude with your Paddle API key, setting the tool scope to read-only if you want queries alone. Unl then checks what it returns against your ratified reconciliation rule.
Does Unl issue refunds or adjust transactions in Paddle?
No. The connection reads one way: Unl pulls transaction and report data through Paddle's MCP server and compares it to your ratified rule. It doesn't touch a transaction, a subscription or a report.
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.