How to Use the Nyckel ML MCP in Vercel AI SDK

Q: How do I perform a semantic search with Nyckel ML in Vercel AI SDK?

You initialize the client and pass the semanticsearch tool to your streamText function. The results come back as a structured list you can map directly to your components.

Q: Can Nyckel ML handle image classification in Vercel AI SDK?

Yes, you use invokemlfunction to send image data for classification. It works consistently across your frontend components.

Stream real-time classification results into your Vercel AI SDK frontend without waiting for spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nyckel ML MCP to Vercel AI SDK

Create your Vinkius account to connect Nyckel ML 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 Nyckel ML with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time ML classification in Vercel AI SDK

Use `invoke_ml_function` to push classification results directly into your stream. Your users see the data updates as they happen rather than waiting for a full response cycle. This approach lets you build responsive UIs where the AI client processes inputs and renders outputs instantly. It turns your static pages into active, machine-learning-driven interfaces.

Manage training samples from your Vercel AI SDK app

Add new training data to your models with `create_ml_sample` directly from your application logic. This keeps your datasets current as users interact with your platform. You can also use `annotate_ml_sample` to refine labels on the fly. It allows your interface to learn from user feedback without leaving the execution context.

Semantic search integration for Vercel AI SDK

Plug `semantic_search` into your search bars to return relevant content based on meaning rather than keywords. It handles complex queries that standard database lookups miss. The tool returns high-confidence matches formatted for your UI components. You get the benefits of advanced indexing without managing the underlying ML infrastructure yourself.

Setup guide

Set up Nyckel ML 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 Nyckel ML 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 Nyckel ML 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 Nyckel. 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 Nyckel ML 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 Nyckel ML MCP in Vercel AI SDK

You initialize the client and pass the `semantic_search` tool to your `streamText` function. The results come back as a structured list you can map directly to your components.

Yes, you use `invoke_ml_function` to send image data for classification. It works consistently across your frontend components.

It connects via standard HTTP transport. You can call the tools from any edge function that supports the MCP standard.

You provide your endpoint token via the authProvider. The connection stays restricted to your specific account environment.

Your training samples and classification data stay within your isolated project. We process your inputs through secure, authenticated endpoints only.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.