How to Use the Kevel MCP in Vercel AI SDK

Q: How do I connect this server to the Vercel AI SDK?

Run npm install ai @ai-sdk/mcp and instantiate your client. Use createMCPClient with the server URL, then pass the resulting tools into your streamText call. Always remember to call mcpClient.close() when you finish.

Stream Kevel ad data directly into your React or Next.js 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 Kevel MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Kevel Inventory to Your Users

This MCP Server connects your Vercel AI SDK application directly to the Kevel Management API. Your agent can read live ad inventory by calling `list_campaigns` and `list_flights` while the user watches the data appear in the UI. You don't have to wait for a massive payload to resolve. The SDK streams the output of `list_sites` and `list_zones` instantly, letting your frontend render placement maps without a loading spinner.

Real-Time Creative Audits via MCP Server

Build internal dashboards that pull ad assets on demand. When your AI client triggers `list_creatives` or `list_ads`, the Vercel AI SDK pipes those details straight into your Vue or Svelte components. This skips the usual API boilerplate. Just pass the MCP client into `streamText` and let the agent figure out which `list_ad_types` or `list_channels` the user actually wants to see.

Fetch Specific Advertiser Profiles Fast

Sometimes you just need to know who owns a specific ad block. Your agent uses `list_advertisers` to find the right ID, then hits `get_advertiser` to pull the exact profile. The edge function handles the routing. You get the exact advertiser metadata rendered in your Next.js app before the user even finishes typing their query.

Setup guide

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

Run `npm install ai @ai-sdk/mcp` and instantiate your client. Use `createMCPClient` with the server URL, then pass the resulting tools into your `streamText` call. Always remember to call `mcpClient.close()` when you finish.

No, this integration is strictly read-only. The server exposes endpoints like `list_campaigns` and `get_campaign` so your agent can fetch data, but it cannot write new records. You will need to handle creation elsewhere.

It gives your LLM native understanding of your ad architecture. Instead of hardcoding API requests, the agent decides when to call `list_flights` or `list_zones` based on the user's prompt.

Yes, that is the main advantage here. When the agent pulls bulk data through `list_ads`, the Vercel AI SDK streams those results directly into your React frontend.

Your ad creatives and advertiser profiles stay secure. The MCP connection relies on a V8 Isolate Sandbox with zero-trust ephemeral access, meaning the SDK only reads what your specific endpoint token allows.

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