How to Use the Finance Toolkit MCP in Pydantic AI

Q: How do I initialize the Finance Toolkit inside Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCPToolset class pointing to your Vinkius MCP Server HTTP endpoint. Pass this toolset into your Agent constructor using the toolsets argument to give your agent access to all four financial calculation tools.

Guarantee type-safe financial calculations in Pydantic AI with strict runtime validation for interest and amortization math.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Finance Toolkit MCP to Pydantic AI

Create your Vinkius account to connect Finance Toolkit 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 Finance Toolkit with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict runtime validation for the Finance Toolkit in Pydantic AI.

If your agent generates a bad parameter, your pipeline should break immediately instead of passing junk data down the line. Integrating this MCP Server with Pydantic AI means every input and output for functions like `calculate_roi` is strictly validated against Pydantic models at runtime. No silent failures, no weird float corruptions. Setting this up is straightforward. Use the unified `MCPToolset` class to point to your hosted Vinkius endpoint, and pass it directly to your agent. If the LLM tries to pass a string instead of a periodic decimal rate to `calculate_amortization`, the framework catches it instantly.

Run bulletproof amortization calculations.

Amortization schedules are highly sensitive to formatting errors. When your agent calls `calculate_amortization`, Pydantic AI ensures the returned SAC or PRICE table matches the expected schema exactly. If the model attempts to invent a column or hallucinate a row, the validation layer throws an error. This type-safety is crucial when building production-grade accounting software. You get clean, predictable outputs that you can map directly to your database models without writing custom parser code or risking breaking your frontend.

Enforce clean inputs for compound and simple interest.

Interest calculations require precise inputs like decimal rates and compounding frequencies. When your agent invokes `calculate_compound_interest` or `calculate_simple_interest`, Pydantic AI validates that the compounding frequency is a valid integer and the rate is a proper float. This structure stops hallucinated variables in their tracks. Because the MCP Server runs externally and communicates via streamable HTTP or SSE, your Pydantic AI agent remains lightweight while offloading the heavy math and validation to a secure sandbox.

Setup guide

Set up Finance Toolkit 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": {
        "finance-toolkit-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Finance Toolkit 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 finance-toolkit. 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 Finance Toolkit 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 Finance Toolkit MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and use the unified `MCPToolset` class pointing to your Vinkius MCP Server HTTP endpoint. Pass this toolset into your `Agent` constructor using the `toolsets` argument to give your agent access to all four financial calculation tools.

Pydantic AI validates all incoming tool data at runtime. If a tool like `calculate_roi` returns data that violates the schema, the framework fails loudly with a validation error, preventing corrupt financial data from polluting your application.

You should avoid using the deprecated MCPServerHTTP class. The modern, unified approach is to use the `MCPToolset` class to connect Pydantic AI to your hosted Finance Toolkit, which supports both streamable HTTP and SSE transports.

Yes. The framework checks the arguments against the tool's schema before executing `calculate_simple_interest`. This ensures your agent is sending a valid decimal rate, like 0.05 for 5 percent, preventing unnecessary roundtrips to the server.

Every transaction payload, containing your interest rates, compounding frequencies, and amortization types, is processed in a secure, ephemeral V8 isolate container. Vinkius maintains a zero-trust architecture, ensuring your mathematical inputs are never written to disk or exposed.

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