How to Use the Adikteev MCP in Vercel AI SDK

Q: How do I connect Adikteev to Vercel AI SDK?

Install the @ai-sdk/mcp package. Initialize the MCP client using createMCPClient with your Vinkius HTTP transport URL. Then pass the retrieved tools directly into streamText.

Stream live Adikteev retargeting data straight into your React frontend using 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 Adikteev MCP to Vercel AI SDK

Create your Vinkius account to connect Adikteev 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 Adikteev with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time churn scores in the UI

You don't want users staring at a spinner while your app fetches prediction data. Hook the Vercel AI SDK up to this MCP Server, and you get live streaming responses. When someone asks about at-risk users, the agent calls `get_churn_scores` and pipes the numbers directly into your Next.js dashboard as they generate. The edge function handles the heavy lifting. Your frontend just renders the text stream. You get instant feedback on which users are about to drop off, making internal marketing tools feel incredibly fast.

Build segments with Vercel AI SDK

Creating retargeting lists usually involves clicking through five different menus. Now you just type a prompt into your custom Svelte app. The agent uses `create_segment` in the background, building the exact audience parameters you asked for. Need to check what is already built? It fires `list_segments` and streams the existing lists right back to the user. You skip the clunky dashboard entirely and manage app retargeting through a simple chat interface.

Live campaign reporting

Marketing teams hate waiting for performance reports to compile. Give them a chat box powered by this Vercel AI SDK MCP integration. They ask how the latest retention push did, and the agent hits `get_reporting` to pull the stats. Because Vercel streams the tool execution results, the UI updates step-by-step. They see the clicks, conversions, and spend appear instantly. It turns complex Adikteev analytics into a quick conversation.

Setup guide

Set up Adikteev 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 Adikteev 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 Adikteev 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 Adikteev. 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 Adikteev 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 Adikteev MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package. Initialize the MCP client using `createMCPClient` with your Vinkius HTTP transport URL. Then pass the retrieved tools directly into `streamText`.

Yes. When the agent calls the reporting tools, the Vercel AI SDK streams those results back to your React or Vue frontend. The user sees the campaign data load progressively.

The Vercel AI SDK catches the error on the server side. You can handle the exception in your edge function and return a friendly fallback message to the frontend without breaking the UI.

Vinkius handles the underlying authentication. You just need your endpoint token. If you want to tie it to specific user accounts in your app, use the `authProvider` config.

Vinkius runs the server in an ephemeral V8 Isolate Sandbox. Your user churn scores and audience segments pass through a zero-trust environment. The instance dies the second your edge function finishes the request.

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