How to Use the Delighted MCP in Vercel AI SDK

Q: How does the Delighted MCP Server handle streaming with Vercel AI SDK?

You configure the MCP client using createMCPClient and pass the tools directly to your streamText function. This lets your React frontend render customer scores and comments chunk by chunk as they arrive.

Q: Can I filter Delighted detractors in Vercel AI SDK using this MCP Server?

Yes. The listrecentdetractors tool identifies low-scoring contacts, allowing your Vercel AI SDK agent to immediately flag unsatisfied users in your customer dashboard.

Q: How do I close the connection to the Delighted MCP client in Vercel AI SDK?

Call mcpClient.close() once your generateText or streamText execution finishes. This cleans up the SSE or HTTP transport connections and prevents memory leaks in your serverless functions.

Pipe real-time Delighted feedback and NPS metrics directly into your Vercel AI SDK React or Next.js frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Delighted MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Delighted feedback feeds in Vercel AI SDK

The `get_recent_customer_comments` tool pulls live Delighted comments straight into your Vercel AI SDK edge routes. Your users see negative or positive reviews rendering in their feed instantly without waiting for a full page reload or API polling. You pass this tool directly to `streamText` to let your Vercel AI SDK UI render incoming Delighted feedback as the model processes it. It bypasses slow backend middleware and runs directly in Edge Functions to keep your feedback dashboard latency below 50ms.

Instant NPS metric updates in Vercel AI SDK

The `get_nps_metrics_summary` tool fetches your overall Delighted score, promoter count, and detractor count instantly. Your Vercel AI SDK agent reads these numbers to dynamically update dashboard widgets without a single loading spinner. By calling this tool inside `generateText`, the Vercel AI SDK model calculates Delighted trend lines and spits out clean JSON directly to your React components. This turns raw feedback metrics into immediate visual components on your admin dashboard.

Trigger Delighted surveys from Vercel AI SDK

The `add_person_to_survey` tool adds a new customer email to your Delighted list and queues up an invitation. Your Vercel AI SDK app triggers this action the second a user finishes a checkout or support session in your frontend. The Vercel AI SDK model handles the input validation, matches the user's email, and fires the tool inside your React Server Action. This connects your user-facing interface directly to your Delighted feedback collection pipeline.

Setup guide

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

You configure the MCP client using `createMCPClient` and pass the tools directly to your `streamText` function. This lets your React frontend render customer scores and comments chunk by chunk as they arrive.

Yes. The `list_recent_detractors` tool identifies low-scoring contacts, allowing your Vercel AI SDK agent to immediately flag unsatisfied users in your customer dashboard.

Absolutely. The server runs on a zero-trust sandbox that matches the lightweight requirements of edge environments, ensuring your Vercel AI SDK app remains fast and responsive.

Call `mcpClient.close()` once your `generateText` or `streamText` execution finishes. This cleans up the SSE or HTTP transport connections and prevents memory leaks in your serverless functions.

Your customer email addresses and NPS scores never touch external logging systems. The MCP connection between Vercel AI SDK and the Delighted endpoint runs through an ephemeral, zero-trust sandbox that discards all feedback comments immediately after 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