How to Use the Assembled MCP in Vercel AI SDK

Q: How do I connect the Vercel AI SDK to Assembled?

Install @ai-sdk/mcp and initialize your client with createMCPClient. Pass the Vinkius HTTP transport URL to the setup function. Remember to call mcpClient.close() when your edge function finishes.

Stream live Assembled support metrics directly into your React or Next.js frontends using the 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 Assembled MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Real-Time Agent States

The `list_agent_states` tool lets your Vercel AI SDK app read exactly what your support reps are doing right now. You can pull live status updates into a Next.js dashboard without forcing users to stare at a loading spinner. Your AI client grabs this data and streams it straight to the UI. Building workforce visibility requires knowing who is on the clock. By combining this with `list_schedules`, your React frontend can instantly compare planned shifts against actual current states. Managers see the gap between expected coverage and reality as fast as the AI generates the text.

Surface Contact Volume Forecasts

Grabbing predicted ticket loads happens through the `list_forecasts` tool. Your edge functions can query this Assembled MCP Server to pull upcoming contact volume expectations. That data pipes directly into your Vue or Svelte components as the AI processes it. Support teams need to match expected volume with actual routing. Calling `list_queues` alongside those forecasts gives your application a complete picture of where tickets are piling up. You build the interface, and the AI streams the underlying queue metrics live.

Map Your Assembled MCP Server Roster

Fetching your entire support hierarchy starts with the `list_teams` tool. Vercel AI SDK applications can map out distinct support pods and display them dynamically. Developers do not have to write custom polling logic to keep the frontend updated. Drilling down into individual rep data requires the `list_users` endpoint. Once you authenticate via `get_account_check`, your app can pull specific user profiles and match them to their respective teams. The end user watches the roster build itself on the screen.

Setup guide

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

Install `@ai-sdk/mcp` and initialize your client with `createMCPClient`. Pass the Vinkius HTTP transport URL to the setup function. Remember to call `mcpClient.close()` when your edge function finishes.

Yes, streaming is the core feature. When you pass the MCP tools to `streamText`, the AI fetches the current agent status and pipes it to your UI immediately. Users see the data appear chunk by chunk.

Vinkius handles the underlying connection stability. Your AI client will receive standard error objects if the upstream service blocks the request. You should implement basic retry logic in your Next.js route handlers.

The SDK supports any modern frontend framework. You write the same server-side logic to fetch forecasts or schedules. The client-side hooks then consume that stream regardless of your chosen UI library.

Every request runs inside a V8 Isolate Sandbox that dies after execution. Your agent schedules and user lists never touch persistent storage. The zero-trust architecture ensures that only your authenticated endpoint token can access the workforce data.

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