How to Use the Xero MCP in LangChain

Q: What if I need to find a specific customer in Xero with LangChain?

You'd first call listxerocontacts using the MCP Server. Then, your agent can filter that list and use the contact details to inform subsequent calls, like looking up their invoices.

Run complex financial models and multi-step queries with LangChain and Xero MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Xero MCP to LangChain

Create your Vinkius account to connect Xero to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Xero with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Financial Reports using the MCP Server

The `get_balance_sheet` tool pulls assets, liabilities, and equity totals for a given date. This gives you an immediate snapshot of financial health. You can chain this output with other data—like calling `list_bank_transactions` next—to build a full picture that simple reporting doesn't offer.

Manage Xero Contacts and Invoices

Need to know who you billed? Start by using `list_xero_contacts` to get all your customers and suppliers. From there, run `list_xero_invoices` to fetch the associated sales or purchase records. This two-step process lets your agent decide which contact relates to a specific invoice, making complex data mapping easy.

Track Cash Flow with Bank Data

The `list_bank_transactions` tool pulls every transaction recorded in your bank accounts. This is raw cash movement data. Your agent can process this list, then call `get_profit_and_loss` to see how those transactions impacted the P&L report for a defined date range.

Setup guide

Set up Xero MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Xero tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "xero-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Xero transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Xero. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Xero now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Xero MCP in LangChain

Your agent decides the flow. You start by giving it a goal, maybe 'What was our revenue last quarter?' It'll figure out if it needs to call `get_profit_and_loss` or check `list_xero_invoices`. The output of one tool becomes the input for the next step.

Yeah, it can. You're not stuck with just Xero. You pass in a list of servers—MCP or otherwise—and your agent treats them all like one big toolset to solve the problem.

Yes. This MCP Server touches invoice details and bank transactions. Your AI client handles secure token authentication when making calls.

You'd first call `list_xero_contacts` using the MCP Server. Then, your agent can filter that list and use the contact details to inform subsequent calls, like looking up their invoices.

Absolutely. You get access to financial reports and account lists. For instance, you can call `list_chart_of_accounts` directly to see every available account type in Xero.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript