How to Use the API Ninjas MCP in Vercel AI SDK

Q: How do I initialize the API Ninjas MCP Server in my Vercel AI SDK project?

Install @ai-sdk/mcp and ai. Initialize the client with createMCPClient pointing to your Vinkius URL, call mcpClient.tools(), and pass those tools directly to streamText.

Q: How does the Vercel AI SDK handle nutrition lookups from API Ninjas?

When a user asks about a food item, the SDK calls the getnutrition tool. The parsed JSON containing protein, carbs, and fat streams straight to your UI component.

Q: What happens if a user submits incomplete measurements for body fat to the MCP Server?

The getbodyfat tool requires waist, neck, and height. If your user leaves these out, the model asks for the missing numbers before calling the tool.

Feed real-time health, metabolic, and nutrition data directly into your Next.js UI with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect API Ninjas MCP to Vercel AI SDK

Create your Vinkius account to connect API Ninjas to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup API Ninjas with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream metabolic math with Vercel AI SDK

The `get_bmr` and `get_tdee` tools let your frontend calculate exact caloric needs instantly. Your app asks for age, weight, and height, then feeds those values to the API Ninjas service to output basal metabolic rate and total daily energy expenditure. Instead of waiting for a slow API roundtrip, your users watch the numbers render on screen as the AI client processes the payload. You just hook up the tools to your streaming text or object generation function.

Pull instant exercise guides on demand

The `get_exercises` tool pulls step-by-step workout instructions based on target muscles or difficulty levels. Your agent filters by beginner, intermediate, or expert to give users exact routines. This tool returns equipment requirements and movement types directly to the client. You can render these instructions as custom React components on the fly while the model explains the form.

Analyze nutrition and body composition instantly

The `get_nutrition` and `get_body_fat` tools calculate macronutrients and body fat percentages. You pass food names or body measurements, and the server returns exact gram counts and body categories. Because this MCP Server runs inside a Vercel Edge Function, latency stays low. Your interface displays the exact fat, protein, and carb breakdown without blocking the rest of the page.

Setup guide

Set up API Ninjas 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 API Ninjas 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 API Ninjas 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 API Ninjas. 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 API Ninjas 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 API Ninjas MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and `ai`. Initialize the client with `createMCPClient` pointing to your Vinkius URL, call `mcpClient.tools()`, and pass those tools directly to `streamText`.

Yes. The client setup is lightweight and compatible with Edge runtimes. Just make sure to call `mcpClient.close()` when your execution finishes to prevent hanging connections.

When a user asks about a food item, the SDK calls the `get_nutrition` tool. The parsed JSON containing protein, carbs, and fat streams straight to your UI component.

The `get_body_fat` tool requires waist, neck, and height. If your user leaves these out, the model asks for the missing numbers before calling the tool.

Your weight, height, age, and gender are processed in ephemeral V8 sandboxes. Vinkius does not store these physical metrics, sending them directly to the API Ninjas endpoint over encrypted TLS and wiping the session immediately.

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