How to Use the Refiner MCP in Vercel AI SDK

Q: How do I authenticate the Refiner MCP Server with Vercel AI SDK?

You pass your API credentials through the authProvider configuration inside createMCPClient. This keeps your Refiner API keys secure on the server side while streaming data safely to your frontend.

Q: How does Refiner stream survey lists to my Vercel AI SDK UI?

The SDK calls listrefinersurveys and streams the JSON array chunk-by-chunk. Your UI components can parse these chunks on the fly, showing active micro-surveys to your admin team without waiting for the entire payload to load.

Q: What happens if the Refiner API goes down?

Your code should check checkrefinerstatus first. If the API is unresponsive, the Vercel AI SDK can gracefully fall back to cached user profiles or show a friendly offline message.

Q: How does this setup protect our customer survey responses?

All raw feedback data and NPS scores retrieved by listrefinerresponses are processed in ephemeral V8 sandboxes. Vinkius handles the transport over secure SSE, ensuring your SaaS customer data is never stored or logged on third-party servers.

Stream Refiner survey responses and user segments to your Vercel AI SDK app using 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 Refiner MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vercel AI SDK Real-time Survey Streaming

Stop making your users stare at loading spinners while fetching customer feedback. This MCP Server lets your Vercel AI SDK app pull live NPS data and feature requests directly from the API. By feeding `list_refiner_responses` into `streamText`, the data renders on the screen block-by-block as it arrives. You configure the client using `createMCPClient` and pass the tools directly to your generative UI components. When the live stream finishes, call `mcpClient.close()` to clean up the connection and keep your Edge Functions light.

Update User Segments on the Edge

Edge middleware needs to be fast, and so does your user targeting. When a user takes a critical action, your AI client can immediately trigger `track_refiner_event` or run `identify_refiner_user` to change their bucket. This happens right inside your Next.js edge route without adding boot latency. Your application gets the updated segments instantly via `list_refiner_segments`. Because this MCP Server integrates natively, you don't have to write custom API wrappers to sync Refiner with your local database state.

Instant Contact Lookup in Chat Interfaces

Build a support dashboard where your team chats with an agent to inspect user accounts. The agent calls `get_refiner_contact` to grab a customer's profile details and displays their exact NPS history right inside the chat bubble. You can use `list_refiner_contacts` to search across your entire customer base. The Vercel AI SDK pipes these contact structures straight into React components, giving your customer success reps a live-updating view of user sentiment.

Setup guide

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

You pass your API credentials through the `authProvider` configuration inside `createMCPClient`. This keeps your Refiner API keys secure on the server side while streaming data safely to your frontend.

Yes, the server runs in an isolated sandbox, and the Vercel AI SDK client is fully compatible with Edge runtimes. Just make sure to call `mcpClient.close()` at the end of the execution block to prevent hanging connections.

The SDK calls `list_refiner_surveys` and streams the JSON array chunk-by-chunk. Your UI components can parse these chunks on the fly, showing active micro-surveys to your admin team without waiting for the entire payload to load.

Your code should check `check_refiner_status` first. If the API is unresponsive, the Vercel AI SDK can gracefully fall back to cached user profiles or show a friendly offline message.

All raw feedback data and NPS scores retrieved by `list_refiner_responses` are processed in ephemeral V8 sandboxes. Vinkius handles the transport over secure SSE, ensuring your SaaS customer data is never stored or logged on third-party servers.

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