How to Use the Splitwise MCP in OpenAI Agents SDK

Q: How does Splitwise use the OpenAI Agents SDK for balance checks?

The agent uses getexpenses to pull a list of all shared expenses. It then processes this raw data against user records, calculating who owes what money in the group.

Q: Can I use Splitwise with the OpenAI Agents SDK for creating new debts?

Yep. You call createexpense, passing a JSON object that includes the cost and the specific shares paid by multiple users, which logs the debt immediately into the MCP Server.

Q: What data does Splitwise store regarding group membership when using OpenAI Agents SDK?

The server tracks userids and associated groups. You use getgroups or getfriends to see the full list of people involved in a shared expense.

Q: How does Splitwise manage group changes with OpenAI Agents SDK?

You first use getgroups to view all groups. If you need details on one, getgroup provides the scope of that specific MCP Server instance.

Q: If I run into issues with Splitwise and OpenAI Agents SDK, what data type should I check?

Check the expense costs. The server relies heavily on these numerical values to determine who owes money. If the cost field is wrong, all subsequent balance calculations will be off.

Manage group finances with Splitwise using your OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Splitwise MCP to OpenAI Agents SDK

Create your Vinkius account to connect Splitwise to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Splitwise with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Track Expenses and Groups via MCP Server

Use `create_expense` to log shared costs, requiring the cost, description, and a breakdown of who paid what. This tool lets your agent accurately record an expense, defining which users contributed how much to the total. Need to clean house? You can also call `delete_expense` if an entry was logged incorrectly. Your agent handles this cleanup using the dedicated MCP Server endpoint.

Retrieve User and Group Information

Start by listing all available groups using `get_groups`, which gives you a full roster of shared accounts. Once you have a group ID, calling `get_group` pulls the detailed structure for that specific collaboration. To manage members, your agent can call `get_friends` to list everyone, or use `get_friend` when it needs specifics on one person's details.

Manage Individual Accounts

`get_user` fetches all necessary details for a user if you only have their ID. Similarly, `get_current_user` automatically provides the identity of the agent running the process. If you need to verify specific data points, calling `get_expense` allows your client to fetch just one expense record by its unique identifier, keeping things focused and fast.

Setup guide

Set up Splitwise MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Splitwise tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Splitwise tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Splitwise tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Splitwise Agent",
            instructions="You have access to Splitwise tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Splitwise. 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 Splitwise 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 Splitwise MCP in OpenAI Agents SDK

The agent uses `get_expenses` to pull a list of all shared expenses. It then processes this raw data against user records, calculating who owes what money in the group.

Yep. You call `create_expense`, passing a JSON object that includes the cost and the specific shares paid by multiple users, which logs the debt immediately into the MCP Server.

The server tracks `user_id`s and associated groups. You use `get_groups` or `get_friends` to see the full list of people involved in a shared expense.

You first use `get_groups` to view all groups. If you need details on one, `get_group` provides the scope of that specific MCP Server instance.

Check the `expense costs`. The server relies heavily on these numerical values to determine who owes money. If the cost field is wrong, all subsequent balance calculations will be off.

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