How to Use the Splitwise MCP in Pydantic AI

Q: How does Splitwise use Pydantic AI to calculate debts?

The agent pulls expenses using getexpenses. Because of Pydantic's validation, every field—like cost or share amount—is guaranteed to be the correct data type before calculation happens.

Q: Can I use Splitwise with Pydantic AI for logging new expenditures?

Yes. You invoke createexpense and pass a JSON object that must conform exactly to the schema, validating cost, description, and all user shares at runtime.

Q: What data does Splitwise track regarding group members with Pydantic AI?

The system tracks user IDs and groups. You use getgroups or getfriends to see the full list of people associated with a shared expense.

Q: How does Splitwise manage group structures using Pydantic AI?

You call getgroups first. This ensures that when you fetch details for one specific group via getgroup, the resulting data is perfectly typed and predictable.

Q: If I run into issues with Splitwise and Pydantic AI, what data type should I check?

Check the user IDs. Since Pydantic requires strict typing, any mismatch or missing ID will cause a clear validation error before your agent attempts to calculate balances.

Type-safe financial tracking with Splitwise and Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Splitwise to Pydantic AI — 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Logging Shared Expenses for MCP Server

To record a cost, your agent executes `create_expense`, passing structured data including the total cost, description, and individual user shares. This ensures every payment is logged with strict type checking. If you need to correct an entry, use `delete_expense`. The MCP Server validates that the expense ID exists before removal.

Reviewing Expense History

Use `get_expenses` when your agent needs a complete list of all logged expenses. If you're only checking one item, calling `get_expense` retrieves that single record. You can also verify the context by running `get_group`, which gives the parameters for the group managing those debts.

Accessing User and Friend Data

`get_user` pulls detailed information on any user ID provided. Furthermore, if you need to know who's involved, `get_friends` lists all connected contacts. To get details for a single person, the agent uses `get_friend`, ensuring the data returned matches the expected structure.

Setup guide

Set up Splitwise MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "splitwise-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Splitwise tools.",
)

result = await agent.run("List recent Splitwise transactions")
print(result.output)

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 Pydantic AI

The agent pulls expenses using `get_expenses`. Because of Pydantic's validation, every field—like cost or share amount—is guaranteed to be the correct data type before calculation happens.

Yes. You invoke `create_expense` and pass a JSON object that must conform exactly to the schema, validating cost, description, and all user shares at runtime.

The system tracks `user IDs` and groups. You use `get_groups` or `get_friends` to see the full list of people associated with a shared expense.

You call `get_groups` first. This ensures that when you fetch details for one specific group via `get_group`, the resulting data is perfectly typed and predictable.

Check the `user IDs`. Since Pydantic requires strict typing, any mismatch or missing ID will cause a clear validation error before your agent attempts to calculate balances.

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