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 AI tool to XBert: your practice's work lists and tasks on one side, and your clients' live ledger data and alerts on the other. This is how you connect XBert to Claude, ChatGPT or Microsoft Copilot.

In practice, you ask a question in plain English and your assistant answers it from your real data. It reads your clients' books but never changes them, and anything it would change in XBert, such as a task or a note, is proposed for your review first.

You only need one address: https://mcp-gateway.xbert.io/mcp

What you need

1. An XBert account with at least one client on a paid plan

2. An AI Assistant that speaks MCP

Claude on the web or Desktop, Claude Code, ChatGPT, or Microsoft Copilot via Copilot Studio.
On a personal plan, you're ready to go.
On a Team, Business or Enterprise plan, your organisation may have switched off the ability to add your own connectors.
- If Add custom connector is missing or greyed out, that's what has happened. Ask whoever administers your Claude or ChatGPT plan to allow custom connectors. This is your own IT or workspace admin, not your XBert admin.

3. Your XBert login

The assistant signs in as you, and sees only what you can see in XBert.
If you cannot open and view a work item for a client in XBert, your assistant cannot read it either.

Which clients your assistant can see

Two things decide whether a client shows up via the MCP: whether you have access to it, and what plan it is on.

1. Your Client Access Permissions

Your assistant is limited to the clients on your Client Access Permissions list in XBert. An admin sets this per user, under Settings (the gear icon), then Users. It is the same list that controls which clients you see in the app.

If a client is not on your list, your assistant will tell you it cannot find that client. That is the permission working as intended, and rephrasing the question will not change it. An admin at your firm can add the client to your access in XBert.

There are four ways your access can be set:

All Clients
Selected Clients
Xero Permissions + All Clients
Xero Permissions + Selected Clients

Whichever one applies to you, your assistant sees exactly the clients that setting leaves you able to see in XBert, and nothing else.

👉 Read more here: Invited Users' Client Access Permissions

2. The client's plan

Of the clients you can access, the MCP then follows the plan each one is on:

Plan	Included?	What your assistant sees
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 AI assistant will tell you the client is not on an AI-enabled plan.
Locked or lapsed trial	❌	Not included until the client is on a paid plan.

💡 Can't find a client?

A client can be missing for either reason. If your assistant says it cannot find a client, that is access. If it says the client is not on an AI-enabled plan, that is the plan.

Set it up in Claude (web and Desktop)

💡 Shortcut

If you are already signed in to Claude, this link opens Claude's Add custom connector box with the name and address already filled in. Then skip to step 5. On a Team or Enterprise plan, an Owner of your firm's Claude account has to do this. See the note at the end of this section.

Open Claude at claude.ai or the Claude desktop app.
Select 'Customize' in Claude's left sidebar, then the Connectors tab between 'Skills' and 'Plugins'.
Click '+ Add' and select Add custom connector.
Name it XBert and paste the address: https://mcp-gateway.xbert.io/mcp
Select Continue. Keep what Claude picks on the next screen (Register automatically for the OAuth client) and select Add, then sign in with your XBert account in the window that opens. If it doesn't open, select Connect next to XBert. 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 Claude is not using XBert

The usual cause is that the connector is switched off for that conversation. Open the + menu in the chat, choose Connectors, and turn XBert on. Claude reaches XBert from Anthropic's own servers rather than from your computer, so there is no firewall or network setting on your side to change.

💡 On a Team or Enterprise plan, a Claude Owner goes first

Owner is a role in your firm's Claude account, not in XBert. It's the person who set up or manages your firm's Claude Team or Enterprise plan. If you're not sure who that is, ask whoever looks after your firm's Claude subscription.

Members cannot add a custom connector on those plans. An Owner or Primary Owner (on Enterprise, also anyone whose custom role includes Manage access to Libraries) adds XBert once for the whole firm under Organisation settings → Connectors → Add → Custom → Web, and everyone else then finds XBert under Customize → Connectors and selects Connect. On Free, Pro and Max you add it yourself. Free allows one custom connector at a time.

Set it up in Claude Code

💡 Try this first

If you have already added XBert on claude.ai, you may have nothing to do. Connectors added there load automatically in Claude Code when you are signed in with that same Claude account. Run /mcp and look for XBert before you add anything.

This applies to a Claude subscription login, not an API key.

If it is not there, or you would rather register it locally, run:

claude mcp add --transport http --callback-port 6274 --scope user xbert https://mcp-gateway.xbert.io/mcp

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

--scope user makes XBert available from any folder rather than only the one you ran the command in.

⚠️ --callback-port 6274 is not optional

XBert registers a fixed port to finish the sign-in, and Claude Code otherwise picks one at random. Leave the flag out and the sign-in fails.

If your Claude Code does not recognise --callback-port, update it first. The flag is only in recent versions.

Set it up in ChatGPT

In ChatGPT, custom MCP servers are added on the web, not in the mobile apps. On a Business, Enterprise or Edu workspace, an admin has to allow them first.

💡 Which plans can do this?

OpenAI's help centre documents this for Business, Enterprise and Edu, with write actions in beta. On Pro, you get read and fetch access only, which means XBert can answer questions but not take action.

Plus, Free and Go aren't documented, so if you're on one of those and the option doesn't appear, that's why.

1. On a Business, Enterprise or Edu workspace, an admin goes first

An admin or owner opens Workspace settings and, under Permissions & roles, turns on Create plugins with MCPs (older workspaces show this under Connected Data). On Business, only an admin or owner can add XBert, and they then publish it for everyone else.

2. Add XBert

Go to chatgpt.com/plugins, select the + button, then Add custom MCP server.
Enter the name XBert and a short description, and under Connection enter https://mcp-gateway.xbert.io/mcp
Authentication: choose OAuth. Read the risk warning and select I understand and want to continue, then Create as a plugin.
Sign in with your XBert account when the browser window opens.
On a workspace, an admin or owner shares it with everyone else from Plugins → Personal, using the ••• menu and Publish.
Start a new chat, turn on XBert from the tools menu, and ask away.

💡 Can't find these menus?

OpenAI renames this area regularly. It has been called Connectors, Apps and now Plugins.

If the wording does not match what you see, look for wherever custom MCP servers or plugins are added. Some accounts still need Developer mode switched on first, under Settings → Plugins → Advanced settings (older workspaces: Settings → Apps → Advanced settings). The address and the OAuth sign-in are the same either way.

Set it up in Microsoft Copilot

First, which Copilot do you mean? Microsoft uses the name for several products, and only one of them is a route to XBert.

Product	Route to XBert?	Why
Copilot Studio	✅ This is the one	Microsoft's agent builder. You add XBert as a tool on an agent, and it recognises our sign-in on its own.
Microsoft 365 Copilot (Copilot Chat in Teams, Word, Outlook)	Indirectly	You cannot paste our address in here. Microsoft now supports MCP servers through a packaged plugin or declarative agent, but that needs a package XBert hasn't published yet, so today you reach it through the Copilot Studio agent below, added to Teams and Microsoft Copilot.
"Create agent" / Agent Builder inside Microsoft 365 Copilot	❌ No	It takes knowledge sources only. Microsoft's own advice is to use Copilot Studio when you need to reach an outside service.
Microsoft Copilot for consumers (copilot.microsoft.com)	❌ No	Fixed list of connectors, no way to add your own.
GitHub Copilot in VS Code	❌ No	A different product entirely, and not the same thing as the "GitHub Copilot harness" that runs Copilot Studio's newer experience.

1. Three things to sort out first

Generative orchestration must be on. In the agent that is Settings → Generative AI. New agents have it on already. Without it, MCP tools do not run at all.
Your IT administrator may need to act. MCP servers in Copilot Studio run over Power Platform connectors, so a data policy that blocks those also blocks XBert, quietly. Your admin can check in the Power Platform admin centre under Security → Data and privacy → Data policy.
Licences. Whoever builds the agent needs a Copilot Studio or Microsoft 365 Copilot licence, and your organisation needs Copilot Credits (a prepaid pack or pay-as-you-go). People who only use the finished agent do not need a licence. Worth knowing: the free trial can build and test an agent but cannot publish it. See Microsoft's licensing guide.

2. Add XBert to a Copilot Studio agent

Open your agent at copilotstudio.microsoft.com and go to its Tools page.
Select Add a tool → New tool → Model Context Protocol.
Fill in the form:
- Server name: XBert
- Server description: a sentence or two on what XBert does. Copilot reads this to decide when to call XBert, so it is worth writing properly.
- Server URL: https://mcp-gateway.xbert.io/mcp
- Authentication: OAuth 2.0, then Type: Dynamic discovery.
Select Create, then Create a new connection, sign in with your XBert account, and select Add to agent.

⚠️ You do not need a client ID, a client secret, or any URLs from XBert

That is what Dynamic discovery is for. XBert registers itself.

Do not choose Manual: it asks for credentials we do not issue, and it will dead-end.

These are Microsoft's documented steps for classic agents. Copilot Studio now opens in its newer experience (in preview), where the path is Build → Tools → Add → Model Context Protocol (MCP). To build a classic agent, select … at the bottom of the home page's side bar, then Open classic experience, or choose Other ways to build when you create the agent.

3. Leave all seven tools on

XBert shows Copilot Studio just seven tools: three that find and run the rest of XBert on demand, and four for signing in and choosing your business. That keeps you well inside Microsoft's limit, and new XBert capabilities reach your agent without you doing anything.

Leave Allow all on. Switch any of the seven off and the agent can lose its way into XBert.

4. Getting it in front of the practice

Publish the agent, then under Channels add Teams and Microsoft Copilot.

💡 Sharing it with the practice

You can install it yourself and share its install link with named colleagues. Listing it for the whole practice needs an administrator's approval.

Test it in the Test agent panel or in Teams. Sign-in does not work on the Demo Website channel, so that one will look broken when it is not.

Microsoft's own instructions: add an MCP server to an agent.

Any other MCP-aware assistant

Find where your assistant manages connectors or MCP servers.
Add a remote MCP server with the address https://mcp-gateway.xbert.io/mcp
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 asks for an OAuth client ID, leave it empty. XBert registers itself.

⚠️ One catch worth knowing

An assistant that runs on your own machine finishes the sign-in on a port on your computer, and XBert accepts port 6274. Claude Code lets you set it (that is what --callback-port 6274 does above) and so does Goose (set GOOSE_OAUTH_CALLBACK_PORT to 6274). Assistants that use a fixed port of their own and give you no way to change it cannot finish signing in today. That currently includes VS Code, Cursor, LM Studio, Cline and Zed. Assistants that run in the cloud, like Claude on the web, ChatGPT and Copilot, are unaffected.

Your first five prompts

Start by asking questions. Hold off on asking it to create a task, add a comment or change anything until you've seen how it answers.

What can you do with my XBert account?
Which of my clients can you see in XBert?
Summarise last week's XBert alerts for [client].
Who on my team is over capacity next week, and which of their tasks are overdue?
Which of my tasks start today, and which are due today? Put my priority tasks first.

💡 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 comments on tasks and XBerts
Team capacity and upcoming due dates

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

Area	What you can ask about
Receivables	Invoices, quotes and receivables
Payables	Bills, purchase orders and payables
Receipt Capture	Receipts, bills and invoices captured into XBert that haven't been published yet. Ask what's come in, what's waiting to be published, what's held for review or couldn't be read, and what XBert read off each one.
Bank	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	XBert alerts and exception review
Custom XBerts	Your practice's Custom XBerts: what each one checks and how it's performing.
Your own practice	Jobs, timesheets and WIP, for firms running Xero Practice Manager

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

Example: check a supplier statement
Attach the supplier's statement in your assistant and ask: Which invoices on this statement aren't in [client]'s bills?

💡 It isn't just one client at a time

Every client you have access to is there to query, across different ledgers, and XPM too.

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 on your Client Access Permissions list, read numbers and records when you ask, and propose actions for you to approve.

It cannot see a client that is not on your client access list.
It never learns your XBert password, because you sign in with XBert itself.
It does not change the books: it never creates or edits transactions in your clients' accounting software. The changes it can make, such as tasks, comments and notes, are proposed for your review first.
It doesn't connect XBert to other apps directly, such as your pricing or proposal software. If the other app has its own MCP connector, add both to the same assistant and ask questions that use both.

Every action is recorded with an audit trail.

Managing and removing access

Turn it off in one place. Remove or disable the XBert MCP Connector in your assistant's settings and it stops connecting. Reconnect any time by signing in again. To end someone's access for certain, such as a lost laptop or someone leaving, remove them in XBert.
Access follows your client access. Change someone's Client Access Permissions 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.
Your password stays with XBert. 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.

Need help?

If you have any questions, our support team is here to help!

Reach out via the chat widget on the bottom left of your XBert screen (Help), or email us at support@xbert.io

How to: Set up the XBert MCP