How to Use the Splitwise MCP in LangChain

Q: How does Splitwise handle complex debt restructuring using LangChain?

Your agent can build a chain of calls: first, use getexpenses to pull all transactions. Next, it uses the data to calculate imbalances, and finally, it reports the necessary adjustments for you.

Q: Can I check group status using Splitwise and LangChain?

Yep. You call getgroups to list all active groups. Then, by passing a group name to getgroup, your agent pulls the current balance details for that specific shared context.

Q: What data does Splitwise and LangChain expose regarding user accounts?

The server exposes basic user details through getuser and allows checking the currently active user via getcurrentuser. This includes IDs needed for expense tracking.

Q: Does this MCP Server support viewing deleted expenses in Splitwise and LangChain?

No. While you can call deleteexpense to remove records, the tools do not provide a mechanism to recover or view previously removed entries.

Build multi-step financial logic with LangChain's structured agent calls to Splitwise.

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 LangChain

Create your Vinkius account to connect Splitwise to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Track expenses using the MCP Server

The `create_expense` tool lets your agent record a new shared expense. You pass specific details—like the total cost and who paid what share—and the system handles it. The agent can then use other tools, like `get_expenses`, to confirm that the transaction was logged correctly across all related groups.

Manage group membership

`get_friends` lists every person you know. You can pass these names to `get_group` to pull up details on a specific shared account, like a trip or apartment rent. If the friend list changes, calling `get_friends` first ensures your agent has the most current roster before checking group balances.

Audit transaction history

The `get_expenses` tool retrieves a full list of logged expenses for a given context. This lets you build an audit trail, seeing every entry from past dates. You can then use this data to cross-reference against individual user records pulled via `get_user`, verifying who was involved in each purchase.

Setup guide

Set up Splitwise 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 Splitwise 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({
    "splitwise-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 Splitwise 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 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 LangChain

Your agent can build a chain of calls: first, use `get_expenses` to pull all transactions. Next, it uses the data to calculate imbalances, and finally, it reports the necessary adjustments for you.

Yep. You call `get_groups` to list all active groups. Then, by passing a group name to `get_group`, your agent pulls the current balance details for that specific shared context.

The server exposes basic user details through `get_user` and allows checking the currently active user via `get_current_user`. This includes IDs needed for expense tracking.

No. While you can call `delete_expense` to remove records, the tools do not provide a mechanism to recover or view previously removed entries.

The server touches basic identity details: User IDs, friend names, group names, and expense records (including cost and paid share).

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