How to integrate Splitwise MCP with Autogen

This guide walks you through connecting Splitwise to AutoGen using the Composio tool router. By the end, you'll have a working Splitwise agent that can add a new friend using their email, create a dinner expense split equally, list all groups i'm part of through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Splitwise account through Composio's Splitwise 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
Splitwise logoSplitwise
Oauth2Api Key

Splitwise helps you split bills and expenses with friends and family. It makes it easy to track shared costs and settle up, so everyone stays on the same page.

27 Tools

Introduction

This guide walks you through connecting Splitwise to AutoGen using the Composio tool router. By the end, you'll have a working Splitwise agent that can add a new friend using their email, create a dinner expense split equally, list all groups i'm part of through natural language commands.

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

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

Also integrate Splitwise with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle 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 Splitwise
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Splitwise tools
  • Run a live chat loop where you ask the agent to perform Splitwise 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 Splitwise MCP server, and what's possible with it?

The Splitwise MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Splitwise account. It provides structured and secure access to your expenses and group data, so your agent can perform actions like creating expenses, adding friends, retrieving categories, and managing your account on your behalf.

  • Expense tracking and creation: Quickly have your agent record new expenses, split bills, or log payments—either between you and friends or within groups.
  • Friend and contact management: Easily add new friends with their email and name, or remove existing friends to keep your network current.
  • Group info and collaboration: Retrieve details about any group you belong to, making it simple to manage shared costs and stay organized with your housemates, travel buddies, or teams.
  • Expense category and currency lookup: Ask the agent to fetch available expense categories or supported currencies, helping you record transactions accurately and consistently.
  • Account and profile insights: Let your agent pull your current user details so you can quickly review account information or verify profile data as needed.

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 Splitwise 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 Splitwise 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 Splitwise 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 Splitwise session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["splitwise"]
    )
    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 Splitwise 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 Splitwise assistant agent with MCP tools
    agent = AssistantAgent(
        name="splitwise_assistant",
        description="An AI assistant that helps with Splitwise 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 Splitwise 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 Splitwise 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 Splitwise 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 Splitwise 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 Splitwise session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["splitwise"]
    )
    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 Splitwise assistant agent with MCP tools
        agent = AssistantAgent(
            name="splitwise_assistant",
            description="An AI assistant that helps with Splitwise 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 Splitwise 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 Splitwise 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 Splitwise, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

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

Add Friend

Tool to add a new friend to Splitwise.

Add User to Group

Tool to add a user to a group.

Create Comment

Tool to create a comment on a specific expense.

Create Expense

Tool to create a new Splitwise expense.

Create Friends

Tool to add multiple friends at once to Splitwise.

Create Group

Tool to create a new group in Splitwise.

Delete Comment

Tool to delete a comment by its ID.

Delete Expense

Tool to delete an existing expense by its ID.

Delete Friend

Tool to delete an existing friend by ID.

Delete Group

Tool to delete a group and all associated records by its ID.

Get Categories

Tool to retrieve expense categories.

Get Comments

Tool to retrieve all comments associated with a specific expense.

Get Currencies

Tool to retrieve a list of supported currencies.

Get Current User

Tool to retrieve information about the current authenticated user.

Get Expense

Tool to retrieve detailed information about a specific expense by ID.

Get Expenses

Tool to list the current user's expenses from Splitwise account.

Get Friend Details

Tool to retrieve detailed information about a specific friend.

Get Friends

Tool to list current user's friends on Splitwise.

Get Group Details

Tool to retrieve detailed information about a specific group.

Get Groups

Retrieves all groups the authenticated user belongs to, including group details, members, balances, and debt information.

Get Notifications

Tool to retrieve recent activity notifications from the user's Splitwise account.

Get User Information

Retrieves basic profile information about any Splitwise user by their ID.

Remove User from Group

Tool to remove a user from a group.

Restore Deleted Expense

Tool to restore a previously deleted expense and its associated records.

Restore Deleted Group

Tool to restore a previously deleted group and all its associated records.

Update Expense

Tool to update an existing Splitwise expense.

Update User

Tool to update user account details including name, email, password, and preferences.

FRAMEWORKS

How to build Splitwise MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Splitwise MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Splitwise MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Splitwise MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Splitwise MCP with Claude Cowork

Codex logo

Codex

Use Splitwise MCP with Codex

OpenClaw logo

OpenClaw

Use Splitwise MCP with OpenClaw

Hermes logo

Hermes

Use Splitwise MCP with Hermes

CLI logo

CLI

Use Splitwise MCP with CLI

Google ADK logo

Google ADK

Use Splitwise MCP with Google ADK

LangChain logo

LangChain

Use Splitwise MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Splitwise MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Splitwise MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Splitwise MCP with LlamaIndex

CrewAI logo

CrewAI

Use Splitwise MCP with CrewAI

FAQ

Frequently asked questions

With a standalone Splitwise MCP server, the agents and LLMs can only access a fixed set of Splitwise tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Splitwise 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 Splitwise tools.

Yes, absolutely. You can configure which Splitwise 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 Splitwise data and credentials are handled as safely as possible.

Start with Splitwise.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Splitwise 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