How to Use the CD Return Calculator MCP in Pydantic AI

Force strict type validation on every certificate of deposit calculation using 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 CD Return Calculator MCP to Pydantic AI

Create your Vinkius account to connect CD Return Calculator 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 CD Return Calculator with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate yield math at runtime

This MCP exposes `calculate_cd_yield` so your agent can compute exact compounding growth on fixed deposits. You provide the terms. The system returns the projected value based on the specified compounding frequency. Pydantic AI guarantees that the output matches your exact data models. If the API returns a string instead of a float for the final yield, the agent fails loudly. You never get silent corruption in your financial reports.

Fetch benchmarks with strict schemas

Grabbing liquid alternative rates requires `fetch_market_benchmarks` to check current interest levels. It retrieves hardcoded money market and high-yield savings figures. Look, you need accurate baselines to make investment decisions. This framework is entirely model-agnostic. You can run these benchmark checks using local models or major commercial APIs. The validation layer ensures the resulting rate data always conforms to your expected structure.

Build Pydantic AI comparison models

Your agent uses `generate_investment_comparison` to stack the fixed deposit against market alternatives. It builds a head-to-head projection of potential returns. Here is the kicker. You configure this using the unified approach with MCPToolset. The deprecated manual HTTP method is gone. You just pass the Vinkius URL and the agent handles the rest over a secure streamable connection.

Setup guide

Set up CD Return Calculator 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": {
        "cd-return-calculator-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent CD Return Calculator 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 CD Return Calculator. 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 CD Return Calculator 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 CD Return Calculator MCP in Pydantic AI

Install the slim package with the MCP extra. Create an MCPToolset instance pointing to your Vinkius URL. Assign it to the toolsets parameter in your agent configuration.

The framework will throw a validation error immediately. It refuses to process financial outputs that do not match your defined Pydantic models.

The framework does not care which model you use. You can calculate yields using a local instance or a commercial provider without changing your code.

Use the streamable HTTP transport provided by the unified toolset class. The older specific HTTP classes are deprecated and should be avoided.

We process your term lengths and deposit amounts in memory during the calculation phase. Vinkius enforces strict TLS encryption on the stream. No financial inputs are persisted on our infrastructure after the response ships.

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