How to Use the Splitwise MCP in AutoGen

Q: Does this MCP Server allow modifying old Splitwise data through AutoGen?

Yes, the deleteexpense tool lets an agent remove a record if it's found to be erroneous. The agents then debate whether or not that deletion is justified.

Run multi-agent consensus on Splitwise finances using AutoGen's deliberation framework.

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 AutoGen

Create your Vinkius account to connect Splitwise to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate expense logging with the MCP Server

The `create_expense` tool lets your agents log a new shared cost. You feed it structured JSON containing all necessary details, like who paid and how much they owe. A performance agent can use this capability to quickly validate that the input structure is correct before committing the expense record.

Consensus on group status

You pass `get_groups` results to multiple agents. A security agent can check if all required members are accounted for, while a calculation agent uses those groups and calls `get_expenses` to calculate the net balance. The agents then debate the final, agreed-upon financial status.

Analyze user relationships

`get_friends` gives a list of contacts. Agents can use this data set against `get_user` to build profiles. For example, one agent might check friend details while another checks if that friend is listed as an active participant in any group.

Setup guide

Set up Splitwise MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Splitwise tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Splitwise_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Splitwise data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

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

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Splitwise_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Splitwise data")
    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 AutoGen

You can set up agents to debate the optimal settlement strategy. One agent might propose paying based on minimum debt, while another suggests maximizing social goodwill, converging on a recommended action.

Yes. You can set up an 'Auditor' agent that cycles through calling `get_groups` and then running calculations based on the results, forcing consensus on the total debt.

The server provides identity details (users/friends), group structures (`get_group`), and all raw transaction records. This allows multiple agents to challenge or verify any piece of financial information.

Yes, the `delete_expense` tool lets an agent remove a record if it's found to be erroneous. The agents then debate whether or not that deletion is justified.

The server handles structured financial data: costs, shares paid, group names, friend IDs, and individual user records. These are the inputs for your multi-agent decision system.

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