How to Use the GatherUp MCP in Vercel AI SDK

Q: How do I stream GatherUp review metrics using the Vercel AI SDK?

Import the MCP client from @ai-sdk/mcp and call getreviewmetrics within streamText. The SDK handles the chunking, letting you pipe the location stats directly to your React components.

Q: Does Vercel AI SDK support real-time feedback replies with GatherUp?

Yes. By exposing replytofeedback to your agent, the model can generate and send responses while streaming the output directly to your support dashboard UI.

Q: What is the best way to clean up connections after pulling reviews with this MCP Server?

Always call mcpClient.close() once your streaming session finishes. Failing to close the client can leave dangling HTTP connections, which slows down your Next.js serverless instances.

Stream GatherUp review metrics and customer feedback directly into your Next.js frontend in real-time with 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 GatherUp MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live metrics with Vercel AI SDK

This MCP Server exposes `get_review_metrics` to fetch your latest location stats and streams them chunk-by-chunk directly into your user interface. You don't have to wait for a massive JSON payload to finish downloading before showing your team how their branches are performing. Your Next.js frontend renders the inbound data immediately, giving support managers instant visibility into local performance. If a location's score dips, the UI updates on the fly without blocking the main thread or showing a stale loading spinner.

Send review requests directly from your edge functions

Triggering `send_review_invite` inside an Edge Function lets you dispatch review requests immediately after a checkout event. Because the Vercel AI SDK runs on the edge, latency stays under 50ms, meaning your customers get their text or email invite while their experience is still fresh. You can pair this tool with `add_new_customer` to sync the buyer's contact info right before sending the invite. This direct pipeline cuts out third-party middleware and keeps your customer database updated in real-time.

Live-reply to negative feedback on the fly

Using `reply_to_feedback` allows your support agents to draft and post responses to internal complaints as they stream onto the screen. The SDK pipes the agent's text directly to your database, so managers see the response draft building word-by-word. If the customer left a public Google review instead, the agent switches to `reply_to_online_review` to handle the external thread. This keeps your response times low and ensures unhappy customers get answers before they close their browser tab.

Setup guide

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

Import the MCP client from `@ai-sdk/mcp` and call `get_review_metrics` within `streamText`. The SDK handles the chunking, letting you pipe the location stats directly to your React components.

Yes, the MCP client is fully compatible with Vercel Edge Functions. You call `send_review_invite` directly inside your edge route, bypassing heavy Node.js runtimes for faster execution.

Yes. By exposing `reply_to_feedback` to your agent, the model can generate and send responses while streaming the output directly to your support dashboard UI.

Always call `mcpClient.close()` once your streaming session finishes. Failing to close the client can leave dangling HTTP connections, which slows down your Next.js serverless instances.

Vinkius runs the server in an isolated V8 sandbox, meaning your customer emails and phone numbers processed by `add_new_customer` never touch persistent disk. All data transmission uses ephemeral, encrypted memory that vanishes the moment the API call 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