We didn't put AI in OneHQ. We put OneHQ where your AI already is.
Looking for AI in your practice management? Here's the honest version. OneHQ has no AI model of its own — on purpose. It speaks MCP, the open standard that lets the assistant you already trust, like Claude or ChatGPT, reach into your practice through your own permissions. You choose the AI. OneHQ stays the source of truth it asks.
"Morning — what have I got on today, and who did I speak to yesterday?"
Claude, over the OneHQ MCP connector
Today: three meetings — Simpson Family Trust at 10:00, Delta Plumbing at 1:30, and a partner review at 4:00 — plus two BAS jobs due. Yesterday you spoke with two clients: a 12-minute call with Ava Chen and a returned call to Marcus Reid.
read your day, meetings and calls · scoped to you
You
"Note on Ava's file that she's switching banks, and move her BAS to Ready for Review."
Claude, over the OneHQ MCP connector
Done — noted on Ava Chen's file, and her BAS job is now Ready for Review, moved along your WIP.
logged a note + moved a job · both reversible, both audited
Illustrative example with invented names. Every read and every action is scoped to what the signed-in staff member can see and do.
"AI inside" vs an MCP connector
Plenty of software now advertises AI baked in. That means a model has been given a door into your client data, and you're trusting the vendor's judgement about what it can reach and what it does with it. OneHQ takes the opposite path — and for a system that holds tax files and identity records, we think it's the only responsible one.
AI bolted into your software
A model you didn't choose, with a door into your data
When it's wrong, it's wrong inside your system of record
You inherit the vendor's answer on privacy and training
Locked to one AI — you move when the vendor does
OneHQ, over MCP
You bring the assistant you already vet — Claude, ChatGPT
OneHQ stays authoritative and audited — it decides what's true
Every request runs through your permissions, every time
An open standard — swap or add assistants as they improve
MCP is the Model Context Protocol — an open standard for connecting AI assistants to real systems through defined, permission-checked tools. OneHQ publishes an MCP connector; the AI lives with your assistant, never inside your client data.
Run your day by asking
OneHQ's connector is live for Claude and ChatGPT. It's a set of tools your assistant can call against your real practice — each gated by the same permissions your screens use. Most of what you'll do with it is run your day, out loud:
Brief me on my day
"What have I got on, and who did I speak to?" Your meetings, calls and what's come in, pulled together without opening a thing.
Make a note on a file
"Note that they're switching banks." Logged straight onto the client's record, in your words — and it can be superseded later, never silently lost.
What's on my list
Your tasks, your jobs and the next actions across the clients you look after — the list you'd otherwise assemble from three screens.
Move it along
Set a job's WIP status, add a task, set a due date, reassign a job. The work advances while you talk — every change audited.
It also keeps an eye on what's out for signature — so "what's still unsigned?" is a question, not a hunt. And when there's real accounting to do, it can do that too — safely:
You, in Claude
"Recode the bank fees sitting in Uncategorised to Bank Fees for the March quarter."
Claude, over the OneHQ MCP connector
Drafted a journal — 9 lines, $312.40, moved from Uncategorised Expense to Bank Fees. It's in review for an accountant to post; nothing has touched the ledger.
recorded a DRAFT journal · a human posts it
Why MCP is the safe way to use AI on a practice
The connector is deliberately narrow. Every request runs through a system that decides — each time — what is true, what this person may see, and what they may do. The assistant asks; OneHQ answers.
It sees what you see. Every call runs through the same access checks as your screens. A client you can't open, the assistant can't read — and it's told an empty result isn't proof the client doesn't exist.
It can't post to accounts. Nothing writes to a client's Xero on the assistant's word. Reclassifications land as draft journals an accountant reviews.
It can't contact your clients on a whim. The only outbound channel is SMS, behind a two-step confirmation. Email and document dispatch are refused entirely.
A scope is a ceiling, not a grant. Connecting grants an assistant only what that staff member could already do — never more. Figures come back with where they came from, so an answer you didn't compute is one you can still check.
And OneHQ's own logic isn't AI either. Its compliance checks and tax figures are deterministic — rules and arithmetic you can audit, not a model's guess. The judgement stays with your accountant; the AI just saves the round trips before it.
Frequently asked
No — and that's deliberate. OneHQ has no AI model of its own. It publishes an MCP connector so the assistant you already trust, like Claude or ChatGPT, can work with your practice. OneHQ stays the authoritative, auditable source of truth; the AI is yours, and stays outside your client data.
MCP is the Model Context Protocol — an open standard for connecting AI assistants to real systems through defined, permission-checked tools. Instead of a vendor bolting a model into your software, MCP lets your chosen assistant call a system's tools under its rules. OneHQ is an MCP connector for your practice.
No. Nothing posts to a client's Xero on the assistant's instruction. A request to reclassify transactions records a draft journal that an accountant reviews and posts. The only outbound action at all is SMS, and that takes a separate, explicit confirmation.
Because your system of record should be deterministic and auditable, and the AI you use should be your choice — vetted by you, on your terms for privacy and data. MCP keeps the two separate, so a model can read and draft without ever becoming the thing that decides what's true in your practice.
Bring your AI. We'll bring the practice.
OneHQ unifies Xero, comms, jobs and compliance into one client record — and opens it to the assistant you already use, safely.