Skip to main content

How to: Set up the XBert MCP

Connect Claude, ChatGPT or Claude Code to XBert in five minutes.

Written by AI Support

What the XBert MCP is

MCP stands for Model Context Protocol, a standard, secure way to let an AI assistant work with another app on your behalf. The XBert MCP connects your assistant to XBert: your practice's work lists and tasks on one side, and your clients' live ledger data and alerts on the other.

In practice, you ask a question in plain English and your assistant answers it from your real data. Anything that would change the books is proposed for your review first, and nothing is applied behind your back.

You need one address, whichever assistant you use:

https://mcp-gateway.xbert.io/mcp

What you need

An XBert account with at least one client on a paid plan. The MCP works client by client, and follows the plan each client is on:

  • ✅ Workflow AI (Nano) - your practice and workflow data for that client, with no ledger needed.

  • ✅ Financial AI - everything above, plus that client's ledger data.

  • ❌ Manual - not included. Your assistant will tell you the client is not on an AI-enabled plan.

  • ❌ Locked or lapsed trial - not included until the plan is sorted out.

An assistant that speaks MCP - Claude on the web or Desktop, Claude Code, or ChatGPT.

Your normal XBert login. The assistant signs in as you and can only see what your XBert role allows. If you cannot see a client in XBert, your assistant cannot either.

If connector settings are locked in your workspace, ask your admin to switch them on.

Set it up in Claude (web and Desktop)

  1. Open Claude at claude.ai or the Claude desktop app.

  2. Go to Settings, then Connectors (on some plans this is labelled Integrations).

  3. Choose Add custom connector.

  4. Name it XBert and paste the address: https://mcp-gateway.xbert.io/mcp

  5. Save it, then select Connect and sign in with your XBert account in the window that opens.

  6. Choose the business or Connect portal you want to work with.

  7. Back in the chat, XBert appears in your tools menu. Ask away.

The first time your assistant uses an XBert tool it asks permission. You can approve each time, or set it to always allow. These are the settings we recommend:

If the connector does not respond: check Claude is allowed to reach XBert. Go to Settings → Capabilities → Code execution and file creation, turn on Allow network egress, and either select All domains or add mcp-gateway.xbert.io and auth.xbert.io to the domain allowlist. Without this the connection can fail quietly.

Set it up in ChatGPT

In ChatGPT, custom MCP connectors sit behind developer mode. It is available on the Plus, Pro, Business, Enterprise and Edu plans, and on Business or Enterprise an admin may need to allow custom connectors first.

  1. Open Settings → Security and login and turn on Developer mode. (If it is not there, look under Settings → Connectors → Advanced — OpenAI has moved this setting between the two.)

  2. Go to Settings → Connectors and choose Create.

  3. Fill in the form:

    • Name: XBert

    • MCP server URL: https://mcp-gateway.xbert.io/mcp

    • Authentication: choose OAuth.

  4. Tick the box to confirm you trust the connector, then select Create.

  5. Sign in with your XBert account when the browser window opens, and choose the business or Connect portal you want to work with.

  6. Start a new chat, turn on the XBert connector from the tools menu, and ask away.

ChatGPT names this area differently from Claude and OpenAI changes it from time to time. If the wording does not match exactly, look for wherever ChatGPT manages connectors or MCP servers — the address and the OAuth sign-in are the same either way.

Set it up in Claude Code

  1. Run:

    claude mcp add --transport http xbert https://mcp-gateway.xbert.io/mcp

  2. In your next session, run /mcp and complete the XBert sign-in when prompted.

  3. Ask in plain English — or install the XBert plugins for ready-made slash-command workflows.

On an older version of Claude Code, run claude mcp add --help to check the syntax.

Any other MCP-aware assistant

  1. Find where your assistant manages connectors or MCP servers.

  2. Add a remote MCP server with the address https://mcp-gateway.xbert.io/mcp

  3. Complete the XBert sign-in when your browser opens, then start asking.

If your assistant asks for a transport type, choose HTTP (sometimes shown as "streamable HTTP"). If it speaks MCP, it speaks XBert.

Your first five prompts

Start read-only. Get a feel for how it answers before you ask it to do anything.

  1. "What can you do with my XBert account?"

  2. "List the clients I look after."

  3. "Summarise this week's XBert alerts for [client]."

  4. "Who's over capacity next week, and what's running behind?"

  5. "What's on my worklist today?"

Name the client and the period. "Bayside Cafe, last quarter" beats "that cafe file" every time.

What you can ask it about

For any client on a paid plan, including Workflow AI (Nano):

  • Work lists, tasks, templates and schedules

  • Client notes and task conversations

  • Team capacity and upcoming deadlines

For clients on Financial AI, where a ledger is connected, everything above plus:

  • Invoices, quotes and receivables

  • Bills, purchase orders and payables

  • Bank activity, cash flow and reconciliation

  • Payroll and employees: pay runs, payslips, leave and retirement contributions (superannuation in Australia)

  • Reporting and the ledger: P&L, balance sheet, journals, budget vs actual, and tax and activity statement figures (BAS and IAS in Australia)

  • XBert alerts and exception review

  • Custom XBerts

  • Your own practice: jobs, timesheets and WIP, for firms running Xero Practice Manager

Each area is explained in plain English, with example prompts, at intelligence.xbert.io/features.

Remember this isn't just one client at a time, you have all your client data to query.
Across different ledgers too, and XPM. That's the power of XBert.

What it can and cannot do

Your assistant holds the permissions of the person signed in, and no more. It can see the clients and data your XBert role allows, read numbers and records when you ask, and propose actions for you to approve.

It cannot see any client or data outside your role. It never learns your XBert password, because you sign in with XBert itself. And it cannot change the books without showing you first: write actions are validated, checked for duplicates and proposed for your review.

Every action is recorded with an audit trail.

Managing and removing access

Turn it off in one place. Remove or disable the XBert connector in your assistant's settings and the connection is gone. Reconnect any time by signing in again.

Access follows your role. Change someone's role in XBert and their assistant's reach changes with it. Nothing is granted beyond it.

More than one business? Ask your assistant to list your available businesses, then switch between them.

Sign-in uses OAuth, so your credentials stay with XBert and the assistant never sees your password.

Getting good results

  • Start with questions, not changes

    • Spend your first week asking: balances, alerts, work lists. Move on to drafting tasks and write-backs once the answers have earned your trust.

  • Be specific

    • Client, period, and what good looks like. Specific asks get specific answers.

  • One client before twenty

    • Prove a routine on a single file, then let the assistant repeat it across the portfolio.

  • Review anything client-facing yourself

    • Always. The assistant drafts; you decide what leaves the practice.

Want ready-made workflows?

Plugins package a whole job — the steps and the output already decided — into a slash command built on this same MCP. Same data, same permissions, same audit trail; just less typing. They run in Claude Code and Claude Desktop.

Browse them at intelligence.xbert.io/plugins.

Need help?

If you need further assistance, please reach out to our support team via the help widget on the bottom left of your XBert screen, or email support@xbert.io

Related Articles
Did this answer your question?