How to Use the Junip MCP in Vercel AI SDK

Q: How do I connect the Junip MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and call createMCPClient with your Vinkius HTTP transport URL. Pass the tools from mcpClient.tools() directly into streamText to let your agent fetch store reviews. Don't forget to call mcpClient.close() when the session ends to free up resources.

Q: How do we handle active campaigns using this setup?

Your agent calls listcampaigns to check active review prompts. You can display this status in an admin dashboard built with Vercel AI SDK. It lets you monitor how many review requests are going out without leaving your custom app.

Show live Junip reviews and product questions on your frontend without loading spinners using Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Junip MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live store feedback with Vercel AI SDK

Your users hate waiting for spinners. Hooking this MCP Server up to your Next.js app lets your AI client pull actual customer ratings on the fly. When a user asks about product sentiment, the SDK streams the exact text from `list_reviews` straight to the screen. You don't have to build complex API endpoints or wait for background cron jobs. The Vercel AI SDK grabs the data from `get_product` and renders it instantly. It runs in Edge Functions, keeping your page loads fast and your database clean.

Interactive Q&A widgets

Let your AI client resolve customer doubts on your product pages. By combining the SDK's UI generation with `list_questions`, your agent drafts accurate answers based on past merchant replies. The visitor sees the response compile word by word. If the question is new, the agent pulls details using `get_question` to determine if a human needs to step in. This turns static FAQ sections into live, interactive chats that actually close sales.

Audit review campaigns in the terminal or web UI

Stop guessing if your post-purchase emails are working. Use the Vercel AI SDK to build an internal dashboard where your support team queries active review collection efforts. The SDK calls `list_campaigns` to show what's running. The agent checks the design of your review widgets using `list_themes`. It displays the visual layout options directly in your developer console, helping you spot styling bugs before they hit production.

Setup guide

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

Install `@ai-sdk/mcp` and call `createMCPClient` with your Vinkius HTTP transport URL. Pass the tools from `mcpClient.tools()` directly into `streamText` to let your agent fetch store reviews. Don't forget to call `mcpClient.close()` when the session ends to free up resources.

Yes, that is the main reason to use Vercel AI SDK. When your agent calls `list_reviews`, the raw review data streams straight to your UI. You can render ratings and reviewer names in real-time instead of waiting for a full API round-trip.

Yes, Vercel AI SDK runs perfectly on the edge, and this MCP Server handles the external API heavy lifting. Your edge functions stay small because Vinkius hosts the server. You just fetch `get_product` metadata without bloated dependencies.

Your agent calls `list_campaigns` to check active review prompts. You can display this status in an admin dashboard built with Vercel AI SDK. It lets you monitor how many review requests are going out without leaving your custom app.

Vinkius runs this tool in an ephemeral, zero-trust V8 sandbox. Your Junip API key is kept secure, and only the requested reviews and questions are processed. No data is stored permanently on the sandbox after the tool execution 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