How to Use the Roast Calculator MCP in Vercel AI SDK

Stream precise thermodynamic roasting calculations directly into your React components with Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Roast Calculator to Vercel AI SDK — 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Stream live cooking times to your Vercel AI SDK UI

We use `calculate_cooking_duration` to calculate how long a roast needs to stay in the oven based on mass and heat. This MCP feeds thermodynamic calculations directly into your React components, letting home cooks see live updates as they adjust meat weight. Your interface stays highly responsive even on slow mobile networks. By executing on the edge, the system computes the exact time and pushes the data to the client instantly.

Predict heat spikes instantly with this MCP

The `estimate_carryover_impact` tool predicts the exact thermal spike that occurs after you pull the meat. Look, meat doesn't stop cooking when you take it out of the heat, which is the physical reality of thermal energy moving toward the center. We pinpoint the exact peak temperature to avoid dry, ruined Prime rib. The Vercel AI SDK streams this predicted rise straight to your application's live chart.

Avoid dry meat with real-time resting timers

Our `calculate_rest_duration` tool determines the exact resting buffer required to let muscle fibers relax. Cut a roast too early and you lose the juices, which is a simple thermodynamic rule that requires patience. This tool gives users a countdown based on muscle mass and cooking temperature. It integrates directly with your frontend state to manage active timers.

Setup guide

Set up Roast Calculator MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Roast Calculator tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Roast Calculator transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install the core SDK and MCP packages via npm. Use the createMCPClient function to connect to the HTTP endpoint, then pass the tools directly into streamText.

Yes, it streams calculated values instantly. As the user adjusts target temperatures, the edge function processes the thermal equations and updates the UI without lag.

Yes, this MCP runs perfectly in Next.js Edge routes. The lightweight thermodynamic formulas don't require heavy dependencies, making it highly efficient.

It analyzes the initial oven temperature, meat weight, and target doneness. It then runs physics equations to determine how much heat will push inward after the roast leaves the heat source.

Your meat weights, target temperatures, and calculated durations are processed entirely in memory. We do not store or track any of your culinary inputs on external databases.

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