How to Use the Treasury Return Calculator MCP in Pydantic AI

Q: How do I configure the Treasury Return Calculator inside Pydantic AI?

Install the package using pip install "pydantic-ai-slimmcp". Next, initialize the MCPToolset with your HTTP endpoint. Finally, pass the toolset into your agent's constructor.

Q: Does this integration support the deprecated MCPServerHTTP class?

No, you don't want to use that. Use the unified MCPToolset class instead. The older class is deprecated and may cause compatibility issues. The new toolset supports both Streamable HTTP and SSE transports.

Validate sovereign bond yields and valuations at runtime with Pydantic AI type safety.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Treasury Return Calculator MCP to Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-Safe Bond Valuations with Pydantic AI

The `calculate_bond_valuation` tool calculates fair market price and annualized yield to maturity for sovereign debt. Pydantic AI validates every returned float and integer before your agent can use it. This MCP prevents your system from acting on corrupted or malformed financial data. If a yield calculation fails or returns an unexpected field, the framework raises a loud validation error immediately.

Validated Cross-Currency Conversions

We use `calculate_currency_equivalent_yield` to convert foreign sovereign bond returns into your target currency. The tool handles cross-rates between USD, GBP, and EUR with strict schema enforcement. Your agent gets clean, structured data that fits your exact Pydantic models. You can pass these validated yields to downstream portfolio tools without worrying about silent runtime failures.

Inflation Adjustments with Zero Hallucinations

The `calculate_inflation_adjusted_return` tool applies the Fisher equation to calculate real purchasing power preservation. It ensures your agent receives verified, inflation-adjusted metrics every single time. Because the framework enforces strict type checks on this MCP, your agent cannot hallucinate empty fields or wrong data types. You get mathematical accuracy you can deploy to production.

Setup guide

Set up Treasury 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": {
        "treasury-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 Treasury Return Calculator tools.",
)

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

Install the package using `pip install "pydantic-ai-slim[mcp]"`. Next, initialize the `MCPToolset` with your HTTP endpoint. Finally, pass the toolset into your agent's constructor.

No, you don't want to use that. Use the unified `MCPToolset` class instead. The older class is deprecated and may cause compatibility issues. The new toolset supports both Streamable HTTP and SSE transports.

If the MCP returns data that violates your schema, the framework raises a validation error. This prevents your agent from processing bad bond math. You can catch these exceptions to trigger retries.

Yes, you must run the MCP externally. The toolset then connects to it over HTTP or SSE. This keeps your core agent application decoupled from the calculation engine.

Your bond prices, yields, and inflation inputs are validated locally before transmission. The MCP connection runs over secure local network protocols or HTTPS. Your proprietary transaction data is never exposed to external model providers.

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