Think inside your AI world.

Gusto through Unl

Payroll tells you what someone is being paid. It has never told you whether that figure sits inside the line your organisation actually agreed to hold.

Gusto through Unl reads job compensation and payroll runs against the pay band you have ratified, so 'is this offer inside the band' comes back under the floor, with the condition it hasn't met.

What Gusto holds

Gusto's MCP server is read-only by design, and it opens onto:

  • Employee records and job history, via list_company_employees and get_gusto_employee
  • Compensation figures attached to each role, via list_job_compensations and get_compensation
  • Payroll runs as they land, via list_company_payrolls and get_payroll
  • Pay schedules and pay periods, via list_company_pay_schedules and list_company_pay_periods
  • Time sheets, via list_company_time_sheets and get_time_sheet

What the naked read gives you

Ask Gusto through Unl what a Senior Engineer in London is being offered and the answer arrives clean: base salary, any variable component, the payroll run it lands in. Nothing about that figure is wrong - it is the number Gusto holds. But the band it should sit inside was never Gusto's to keep; that lives with whoever ratified it, and a payroll platform has no view of that decision.

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

What changes when Gusto is read measured

Your head of people ratified the band for Senior Engineer, London, after last year's market-rate review, so no offer could drift without a reason attached to it.

'Is this offer inside the band' returns, measured: under the floor by four thousand, the amount still owed before it clears. Gusto supplied the offer figure; your ratified rule supplied the band.

And back again

That answer does not vanish once the offer is signed. The band, the reason it was set, and the gap this offer showed against it sit inside Unl as one thread, so next time a Senior Engineer offer comes through, the same ratified line is there to measure against - not a fresh negotiation about what fair even means this quarter.

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

Why does the same salary come back inside the band for one hire and outside it for another?

Because the band is ratified per role and location, not as a single company-wide number. Unl reads each offer against the specific band that applies to that role and that location, so two offers at different levels return different verdicts even in the same payroll run.

How do I connect Gusto to Claude?

Gusto's MCP server is hosted at mcp.api.gusto.com. Add it as a connector in Claude, authorise the OAuth request with your Gusto admin account, and choose which data categories to expose. Unl then reads through that same connection - no separate export or spreadsheet required.

Does Unl change payroll or approve compensation?

Unl reads through Gusto, 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.