How to integrate Xero MCP with Autogen

This guide walks you through connecting Xero to AutoGen using the Composio tool router. By the end, you'll have a working Xero agent that can list all active xero tenant connections, show latest contacts added this week, retrieve all open quotes for this month through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Xero account through Composio's Xero MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Xero logoXero
Oauth2

Xero is cloud-based accounting software for small businesses, offering invoicing, bookkeeping, and real-time financial reports. It helps you manage business finances efficiently from anywhere.

41 Tools

Introduction

This guide walks you through connecting Xero to AutoGen using the Composio tool router. By the end, you'll have a working Xero agent that can list all active xero tenant connections, show latest contacts added this week, retrieve all open quotes for this month through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Xero account through Composio's Xero MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Xero with

ChatGPTOpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenCodeCursorVS CodeOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Xero
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Xero tools
  • Run a live chat loop where you ask the agent to perform Xero operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Xero MCP server, and what's possible with it?

The Xero MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Xero account. It provides structured and secure access to your accounting data, so your agent can retrieve contacts, manage connections, update invoices, and monitor quotes automatically on your behalf.

  • Connection management: Instantly list all active Xero tenant connections linked to your account, making it easy for your agent to select and operate on the right organization.
  • Contact retrieval and lookup: Fetch detailed, up-to-date lists of business contacts including filtering, paging, and incremental updates to keep your records synchronized and actionable.
  • Quote management and tracking: Retrieve, filter, or search through your sales quotes so your agent can help you stay on top of prospective business and follow up faster.
  • Invoice updating and automation: Modify details of existing invoices—such as amounts, due dates, and line items—allowing your agent to keep your invoicing accurate and up to date without manual edits.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Xero account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Xero via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Xero connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Xero session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["xero"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Xero tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Xero assistant agent with MCP tools
    agent = AssistantAgent(
        name="xero_assistant",
        description="An AI assistant that helps with Xero operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Xero tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Xero related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Xero tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Xero and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Xero session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["xero"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Xero assistant agent with MCP tools
        agent = AssistantAgent(
            name="xero_assistant",
            description="An AI assistant that helps with Xero operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Xero related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Xero through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Xero, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Xero action and event your agent gets out of the box.

Create Bank Transaction

Create a bank transaction in Xero.

Create Contact

Create a new contact in Xero.

Create Invoice

Create a new invoice in Xero.

Create Item

Create an inventory item in Xero.

Create Manual Journal

Create one or more manual journals (journal entries) in Xero with journal lines.

Create Payment

Create a payment in Xero to link an invoice with a bank account transaction.

Create Purchase Order

Create a purchase order in Xero to order goods/services from suppliers.

Get Account

Retrieve a specific account from Xero's chart of accounts by its unique ID.

Get Asset

Retrieve a specific asset by ID from Xero.

Get Balance Sheet Report

Retrieve Balance Sheet report from Xero.

Get Budget

Retrieve a budget from Xero.

Get Connections

Tool to list active Xero connections.

Get Contacts

Tool to retrieve a list of contacts.

Get Invoice

Retrieve a specific invoice by ID from Xero.

Get Item

Retrieve a specific item by ID from Xero.

Get Manual Journal

Retrieve a specific manual journal by ID from Xero.

Get Organisation

Retrieve organisation details from Xero.

Get Profit & Loss Report

Retrieve Profit & Loss report from Xero.

Get Project

Retrieve a specific project by ID from Xero.

Get Purchase Order

Retrieve a specific purchase order by ID from Xero.

Get Quotes

Tool to retrieve a list of quotes.

Get Trial Balance Report

Retrieve Trial Balance report from Xero.

List Accounts

Retrieve chart of accounts from Xero.

List Assets

Retrieve fixed assets from Xero.

List Attachments

List all attachments for a specific entity in Xero (invoice, contact, etc.

List Bank Transactions

Retrieve bank transactions from Xero.

List Credit Notes

Retrieve list of credit notes from Xero.

List Files

Retrieve files from Xero Files.

List Folders

Retrieve folders from Xero Files.

List Invoices

Retrieve a list of invoices from Xero.

List Items

Retrieve items (inventory/products) from Xero.

List Journals

Retrieve journals from Xero.

List Manual Journals

Retrieve manual journals from Xero.

List Payments

Retrieve list of payments from Xero.

List Projects

Retrieve projects from Xero.

List Purchase Orders

Retrieve list of purchase orders from Xero.

List Tax Rates

Retrieve tax rates from Xero.

List Tracking Categories

Retrieve tracking categories from Xero.

Update Invoice

Tool to update an existing invoice.

Update Contact

Update an existing contact in Xero.

Upload Attachment

Upload a file attachment to a Xero entity (invoice, contact, etc.

FRAMEWORKS

How to build Xero MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Xero MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Xero MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Xero MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Xero MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Xero MCP with Claude Cowork

Codex logo

Codex

Use Xero MCP with Codex

Cursor logo

Cursor

Use Xero MCP with Cursor

OpenClaw logo

OpenClaw

Use Xero MCP with OpenClaw

Hermes logo

Hermes

Use Xero MCP with Hermes

CLI logo

CLI

Use Xero MCP with CLI

Google ADK logo

Google ADK

Use Xero MCP with Google ADK

LangChain logo

LangChain

Use Xero MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Xero MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Xero MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Xero MCP with LlamaIndex

CrewAI logo

CrewAI

Use Xero MCP with CrewAI

OpenCode logo

OpenCode

Use Xero MCP with OpenCode

VS Code logo

VS Code

Use Xero MCP with VS Code

FAQ

Frequently asked questions

With a standalone Xero MCP server, the agents and LLMs can only access a fixed set of Xero tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Xero and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Xero tools.

Yes, absolutely. You can configure which Xero scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Xero data and credentials are handled as safely as possible.

Start with Xero.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Xero tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies