How to Use the Baker Percentage Calculator MCP in Vercel AI SDK

Stream live baking math directly into your React interfaces using the Baker Percentage Calculator MCP and 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 Baker Percentage Calculator MCP to Vercel AI SDK

Create your Vinkius account to connect Baker Percentage 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 Baker Percentage Calculator with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Live Recipe Conversion via MCP

Users hate waiting for backend calculations when tweaking a dough formula. You want the hydration ratio to update the second someone types a new water weight into your Next.js frontend. Hook up `recipe_to_baker_percentage` through the Vercel AI SDK to stream those conversions instantly. Your agent calculates the precise ratios relative to the total flour weight and pushes the results right into the UI.

Dynamic Batch Scaling

Scaling up from a test loaf to a full bakery production run usually breaks standard recipe apps. The math gets messy when dealing with odd scaling factors. Your agent handles this by calling `scale_baker_percentage_to_weights` in the background. It takes the target yield and spits out the exact gram weights needed for the new batch size while maintaining perfect ratios.

Secure Vinkius Execution

Every calculation happens inside a Vinkius V8 isolate sandbox. You get zero-trust execution without managing infrastructure or worrying about rogue code. If a user only knows they added 15 grams of salt at 2 percent, your agent can fire off `check_flour_base` to reverse engineer the total flour required. Vinkius native token optimization cuts the overhead by up to 60 percent on that call.

Setup guide

Set up Baker Percentage 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 Baker Percentage 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 Baker Percentage 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 Baker Percentage 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.