How to Use the Chewy Ads MCP in Vercel AI SDK

Q: What is the best way to close the Chewy Ads connection in Vercel AI SDK?

You must always call mcpClient.close() after your generateText or streamText function resolves. This prevents dangling SSE connections and ensures your Vercel serverless executions spin down cleanly.

Q: How do I pull specific product catalogs into my UI?

Your agent runs listchewycatalogs to fetch the synced product feeds. The SDK then streams the catalog items directly into your React state for immediate rendering.

Feed live Chewy Ads campaign data directly into your Next.js frontend 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 Chewy Ads MCP to Vercel AI SDK

Create your Vinkius account to connect Chewy Ads 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 Chewy Ads with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Ad Group Auditing via Vercel AI SDK

Stop making users wait for heavy retail media dashboard loads. When you bind this MCP Server to your Edge Functions, your app streams live ad groups and keyword bids directly to the browser. Your React components render actual data as the LLM fetches it via `list_campaign_adgroups` and `list_adgroup_keywords`. The UI updates line-by-line instead of blocking the thread. By passing the tools from `mcpClient.tools()` into `streamText`, you let your users watch their Chewy campaign structures organize themselves in real time.

Instant Budget and Balance Checks on the Edge

Run your budget checkers right where your traffic is. This MCP integration lets your AI client call `get_chewy_account_balance` inside lightweight Edge runtimes without dragging down page speed. Because the Vercel AI SDK handles streaming tool outputs natively, your custom billing dashboard can display current Chewy spend metrics instantly. No lagging API calls, just clean, immediate feedback for your merchants.

Live Performance Reporting in Your UI

Show your clients exactly how their pet-product ads are performing without manual exports. Your application triggers `get_performance_report` based on natural language requests and displays the raw numbers as they land. Closing the connection with `mcpClient.close()` once the generation finishes keeps your serverless execution times tight. It lets you build fast, interactive Chewy Ads reporting interfaces that feel like native apps.

Setup guide

Set up Chewy Ads 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 Chewy Ads 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 Chewy Ads 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 Chewy Ads. 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 Chewy Ads 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 Chewy Ads MCP in Vercel AI SDK

You configure authentication by passing your Vinkius credentials through the `authProvider` option when setting up `createMCPClient`. This keeps your Chewy retail media API keys secure on the server side while streaming data safely to your frontend.

Yes, this MCP Server works perfectly with Edge runtimes when paired with the Vercel AI SDK. You call `get_performance_report` inside `streamText` to render pet-product ad performance data dynamically without cold-start delays.

You must always call `mcpClient.close()` after your `generateText` or `streamText` function resolves. This prevents dangling SSE connections and ensures your Vercel serverless executions spin down cleanly.

Your agent runs `list_chewy_catalogs` to fetch the synced product feeds. The SDK then streams the catalog items directly into your React state for immediate rendering.

Your Chewy ad budgets and campaign performance stats never touch public logs or third-party databases. Every tool call runs inside Vinkius's isolated V8 sandboxes, meaning your proprietary retail media spend details are kept strictly private during execution of this MCP Server.

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