How to Use the Judge.me MCP in Vercel AI SDK

Q: How do I handle rate limits when fetching Judge.me reviews with Vercel AI SDK?

We recommend caching the output of listreviews at the Edge. The SDK handles streaming smoothly, but the Judge.me API imposes strict limits, so avoid calling getreview on every single page render.

Q: Can Vercel AI SDK stream Judge.me media files directly to a React component?

Yes. By calling listmedias, the SDK receives the image and video URLs, which you can map directly to your custom React media gallery components during the stream.

Q: How does Vercel AI SDK authenticate with the Judge.me MCP Server?

You configure the endpoint token using the authProvider option in createMCPClient. This ensures secure, credential-free calls from your Next.js Edge Functions.

Q: How do I close the connection once the review fetch is complete?

Always call mcpClient.close() inside your API route or Server Action to shut down the MCP connection. Failing to close the client will leak HTTP connections and eventually crash your serverless execution environment.

Pipe real-time Judge.me reviews and product Q&As directly into your Next.js UI using 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 Judge.me MCP to Vercel AI SDK

Create your Vinkius account to connect Judge.me 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 Judge.me with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct-to-UI Review Feeds

This integration uses `list_reviews` and `list_medias` to feed user-generated content directly to your application's frontend. Your AI client pulls the latest rating scores and customer media files, rendering them instantly without waiting for full page reloads. By calling these tools within Vercel AI SDK's streaming framework, you bypass standard database sync delays. The raw JSON payload converts into live UI elements the moment the data arrives from the API.

Real-time Customer Q&A Resolution

This setup uses `list_questions` and `list_answers` to handle shopper inquiries on your storefront. Your Vercel AI SDK agent fetches unanswered buyer questions and drafts responses based on verified product details retrieved via `get_product`. The agent displays the draft inline for support agents to review. This eliminates the need to switch tabs between your customer service console and the Judge.me dashboard.

Live Storefront Audits via MCP Server

This MCP Server relies on `get_settings` and `list_coupons` to inspect your active discount incentives and widget configurations. Your frontend-facing AI reads your widget setup to verify that review collection emails match your current store parameters. Instead of hardcoding audit logic, you let the LLM parse the raw settings object. It highlights active coupon codes and flags mismatched email templates directly in your admin panel.

Setup guide

Set up Judge.me 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 Judge.me 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 Judge.me 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 Judge.me. 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 Judge.me 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 Judge.me MCP in Vercel AI SDK

We recommend caching the output of `list_reviews` at the Edge. The SDK handles streaming smoothly, but the Judge.me API imposes strict limits, so avoid calling `get_review` on every single page render.

Yes. By calling `list_medias`, the SDK receives the image and video URLs, which you can map directly to your custom React media gallery components during the stream.

You configure the endpoint token using the `authProvider` option in `createMCPClient`. This ensures secure, credential-free calls from your Next.js Edge Functions.

Always call `mcpClient.close()` inside your API route or Server Action to shut down the MCP connection. Failing to close the client will leak HTTP connections and eventually crash your serverless execution environment.

This server accesses customer review text, product ratings, and uploaded media files. All data is transmitted over TLS-encrypted connections and processed in ephemeral V8 isolates that destroy your data the millisecond the request completes.

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