How to Use the Collect MCP in Vercel AI SDK

Q: How do I close the connection after fetching campaign info?

Always call mcpClient.close() once your agent finishes running getcampaign. This prevents memory leaks and hanging connections in your serverless environment.

Get customer files and forms directly into your Next.js frontend with Vercel AI SDK and the Collect 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 Collect MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream real-time submission tracking in Vercel AI SDK

`list_campaigns` lets your Vercel AI SDK client fetch active file collection drives and stream the status directly to your React components. Instead of making users wait for a full API response, your agent pulls real-time campaign lists and renders them on the edge as they load. This setup lets you build live dashboards where your interface updates instantly. By combining `get_campaign` with streaming text outputs, your users watch their document collection progress bar move in real-time.

Interactive request creation on the Edge

`create_request` triggers new document collection workflows right from your user-facing chat window. Your AI client runs this tool inside an Edge Function to immediately generate and dispatch a secure upload link to a customer. You don't need a heavy backend server to handle these requests. The SDK streams the confirmation using `get_request` so the user knows exactly when the recipient receives the upload prompt.

Direct message dispatching from your UI

`send_message` allows your AI client to ping recipients who forgot to upload their documents. Your UI displays these outgoing notifications live, giving users a clear view of conversational follow-ups. Using `list_messages` alongside this tool keeps your interface in sync. Your Next.js app shows the exact message history without needing manual page refreshes or complex state management.

Setup guide

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

Pass your token using the createMCPClient transport configuration. Since Vinkius manages the endpoint, you only need one secure token to authorize all ten tools in your Next.js edge functions.

Yes, you can stream these results directly. When your agent calls `get_element_details`, the SDK streams the field requirements straight into your React UI without annoying spinners.

Yes, this server runs perfectly inside Vercel Edge Functions. The lightweight MCP client protocol ensures fast execution times when calling `list_requests` from your serverless code.

Always call `mcpClient.close()` once your agent finishes running `get_campaign`. This prevents memory leaks and hanging connections in your serverless environment.

Your files never touch Vinkius disks. The platform uses sandboxed V8 isolates to run the server, meaning your document metadata and submission details remain strictly between your app and the Collect API.

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