How to Use the Roast Calculator MCP in Pydantic AI

Enforce strict thermal boundaries for your meat calculations using Pydantic AI validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Roast Calculator MCP to Pydantic AI

Create your Vinkius account to connect Roast 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 Roast Calculator with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-Safe Math with this MCP Server

Start with the base temp. You cannot predict a cooking window without knowing exactly how cold the meat is. Triggering `calculate_cooking_duration` processes that initial variable against total mass to output a strict timeline. Hallucinated numbers cause foodborne illness. Pydantic AI validates every single response against strict runtime models. If your agent tries to invent a cooking time that violates basic physics, the framework fails loudly and stops execution.

Bounding the Carryover Spike

Watch the carryover. Internal temperatures spike violently after removing a roast from high heat. The `estimate_carryover_impact` function calculates that exact trajectory based on the final ambient oven temperature. Silent data corruption ruins production systems. You need absolute certainty that the thermal payload matches your schema. This MCP framework guarantees the carryover integer is actually an integer before passing it downstream to your timers.

Resting Logic and Model Agnosticism

Patience is a measurable culinary requirement. Slicing hot meat leaves the cutting board flooded and the roast dry. Querying `calculate_rest_duration` defines the exact stabilization period required for optimal texture. Locking into one specific vendor is a bad strategy. This architecture works flawlessly whether you connect a local model or a hosted API. Setup requires installing pydantic-ai-slim with the mcp extra and passing an MCPToolset via HTTP to your agent.

Setup guide

Set up Roast 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": {
        "roast-calculator-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the slim package with the MCP extra. Create an MCPToolset using your HTTP endpoint. Provide that toolset array directly to your Agent initialization.

The framework throws a strict validation error immediately. It refuses to pass malformed thermal calculations back to your application logic.

Any model supported by the framework works perfectly. You can swap between different providers without changing a single line of your culinary math logic.

The legacy MCPServerHTTP approach is deprecated. You must use the unified MCPToolset method. It supports both Streamable HTTP and SSE transports natively.

The endpoint ingests raw meat weights, probe telemetry, and resting target temperatures. Zero user account information is transmitted. We secure the connection to ensure your thermal parameters remain private.

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