How to Use the Adtelligent MCP in Vercel AI SDK

Q: How do I connect the Adtelligent MCP Server to my Vercel AI SDK project?

Install the @ai-sdk/mcp package and initialize the client using the HTTP transport. You feed the tools from mcpClient.tools() directly into generateText or streamText to let your agent manage campaigns.

Q: Can I stream Adtelligent SSP reports directly using the Vercel AI SDK?

Yes. By using getsspreport inside a streaming text generation call, the Vercel AI SDK pushes programmatic performance metrics straight to your UI components as the data arrives.

Stream Adtelligent campaign metrics directly into your React components in real-time 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 Adtelligent MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live DSP Campaign Audits in Vercel AI SDK

Stop making your ad ops team wait for slow programmatic performance reports to load. Pull live data using `list_campaigns` and feed it directly into your streaming UI. Your AI client reads the active campaign structures and feeds the raw JSON straight to your frontend components before the connection times out. You write clean React code and let the MCP Server fetch your DSP campaign structures. The edge-compatible client processes advertiser metadata side-by-side with your UI updates, so marketing teams see their active DSP setups populate instantly.

Real-Time SSP Performance Streaming

Feed raw programmatic revenue metrics directly to your dashboard users. When your AI client calls `get_ssp_report`, the server fetches the SSP auth token and returns the performance statistics. The Vercel AI SDK streams these numbers directly into your custom charts without blocking the main thread. This setup bypasses traditional backend polling for SSP data. By letting the SDK handle the streaming response, you display live revenue and fill rate metrics as they arrive from the Adtelligent endpoints.

Instant Advertiser Directory Lookups

Build dynamic DSP search interfaces for your programmatic ad operations team. Using `list_advertisers`, your client fetches active DSP accounts and renders them as interactive cards. You don't have to build custom API wrappers for your advertising data or handle complex pagination logic. The Vercel AI SDK hooks directly into the advertiser tool output. As soon as the server returns the raw advertiser list, your frontend updates the state, giving media buyers immediate access to their accounts.

Setup guide

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

Install the `@ai-sdk/mcp` package and initialize the client using the HTTP transport. You feed the tools from `mcpClient.tools()` directly into `generateText` or `streamText` to let your agent manage campaigns.

Yes. By using `get_ssp_report` inside a streaming text generation call, the Vercel AI SDK pushes programmatic performance metrics straight to your UI components as the data arrives.

You pass your SSP Auth Token through the Vinkius endpoint header or use the `authProvider` in your SDK setup. The server injects the token when calling DSP and SSP tools so your code stays clean.

You can set standard fetch timeouts on the MCP client transport. If `list_advertisers` encounters an API delay, the SDK catches the error and lets your agent try a different query or report the issue back to the user interface.

All SSP reporting tokens and advertiser lists run through Vinkius's isolated V8 sandbox. Your campaign data is processed in ephemeral environments that never store your credentials or marketing metrics after the request finishes.

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