How to Use the Deterministic Fair-Share Tip Splitter MCP in Pydantic AI

Q: How do I configure the Deterministic Fair-Share Tip Splitter with Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset pointing to your HTTP endpoint, and pass it in the toolsets array when instantiating your agent.

Q: Why did my agent throw a validation error on the tax amount?

The tool requires specific numeric types for taxAmount and tipPercentage. If the model attempts to pass a formatted currency string like '$5.00', the runtime schema check will block it.

Force your Pydantic AI agents to calculate perfect restaurant splits with strict type validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deterministic Fair-Share Tip Splitter MCP to Pydantic AI

Create your Vinkius account to connect Deterministic Fair-Share Tip Splitter to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Deterministic Fair-Share Tip Splitter with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict validation with this MCP Server

The `split_bill` tool stops agents from making up fake math when distributing taxes and tips. It requires a strict stringified JSON array of items, a `taxAmount`, and a `tipPercentage`. If the agent tries to pass a string instead of a float for the tax, the framework throws a loud validation error. Pydantic AI ensures you never deal with silent data corruption. Your application gets a guaranteed, type-safe response back from the tool. You can trust the final ledger knowing the inputs and outputs passed rigorous runtime checks.

Eradicating floating-point errors

The `split_bill` tool resolves fractional penny discrepancies using a deterministic largest-remainder algorithm. When three people split a ten-dollar appetizer, the math assigns the odd pennies based on item weight rather than random chance. The final shares always equal the exact receipt total. Model-agnostic frameworks need reliable external tools. Whether you run a local Llama model or Anthropic's latest release, they all fail at this specific math problem. Offloading the calculation to a dedicated deterministic function guarantees correctness across any LLM backend.

Unified toolset integration

Connecting the `split_bill` tool uses the modern MCPToolset approach. You just pass your endpoint URL to the toolset and hand it to your agent. The framework handles the underlying MCP protocol automatically. The system supports both Streamable HTTP and SSE transports. Since the server runs externally on Vinkius, your local Python code stays lightweight. The heavy mathematical lifting happens in the cloud.

Setup guide

Set up Deterministic Fair-Share Tip Splitter 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": {
        "deterministic-fair-share-tip-splitter-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Deterministic Fair-Share Tip Splitter 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 tip-splitter. 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 Deterministic Fair-Share Tip Splitter 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 Deterministic Fair-Share Tip Splitter MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` pointing to your HTTP endpoint, and pass it in the `toolsets` array when instantiating your agent.

The framework automatically validates the tool's expected schema against the agent's output. If the model hallucinates the JSON array structure, the agent fails loudly before hitting the server.

Yes. Since the MCP protocol is standard, you can use any supported LLM. The agent simply formats the prompt and calls the external tool for the actual calculation.

The tool requires specific numeric types for `taxAmount` and `tipPercentage`. If the model attempts to pass a formatted currency string like '$5.00', the runtime schema check will block it.

Your item names, prices, and tip percentages are processed in an ephemeral, isolated environment. The execution context is destroyed immediately after returning the result. We retain absolutely nothing.

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