How to Use the Guidebook MCP in Vercel AI SDK

Q: How do I stream Guidebook schedule updates using the Vercel AI SDK?

You import the MCP client and pass the tools directly to streamText. When the agent calls getevent or listevents, the tool outputs feed straight into your UI components without blocking the main thread.

Q: Can I use the Vercel AI SDK to add custom list items to my Guidebook?

Yes. You can have your agent call createcustomlistitem inside your streaming loop. This lets event organizers type a quick command in your chat interface and watch the new exhibitor profile appear live on screen.

Q: How do I close the connection once the event data is loaded?

You must always call mcpClient.close() when your streaming session finishes. This prevents open HTTP connections from hanging in your serverless environment and keeps your execution costs down.

Build live event interfaces where Guidebook updates stream directly into your React components 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 Guidebook MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Guidebook Updates via the Vercel AI SDK

Your users don't want to wait for a loading spinner when a conference room changes. This MCP Server lets your Next.js app stream schedule updates directly to the frontend. When you run `update_guide` or pull fresh session data with `get_event`, the changes render instantly in the UI. By combining the SDK's streaming capabilities with `list_events`, you build interfaces that feel alive. Attendees see room shifts and speaker swaps the second they happen. No page refreshes, no stale data, just immediate UI feedback.

Build Instant Exhibitor Directories

Managing sponsor booths on the fly shouldn't require a full redeploy. You can let your agent handle the heavy lifting by pulling data with `list_custom_lists` and feeding it straight to your layout. The Vercel AI SDK streams these lists item by item, giving users a fast, responsive directory. If a booth location changes, the agent spins up `create_custom_list_item` to patch the guide. The SDK handles the streaming UI transition, so your event staff see the updated vendor map populate in real-time.

Verify Event App Status on Edge

Running on Vercel Edge Functions means you need lightweight, fast checks before you serve traffic. Hook up this MCP Server to check if the API is responsive before your application tries to load the main dashboard. It keeps your serverless execution times low and your users happy. Once you know the API is healthy, your agent can safely trigger `list_guides` to fetch the active event shells. This setup ensures your edge middleware never hangs on dead connections during peak morning registration rushes.

Setup guide

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

You import the MCP client and pass the tools directly to `streamText`. When the agent calls `get_event` or `list_events`, the tool outputs feed straight into your UI components without blocking the main thread.

Yes. You can have your agent call `create_custom_list_item` inside your streaming loop. This lets event organizers type a quick command in your chat interface and watch the new exhibitor profile appear live on screen.

It does. The MCP Server communicates over standard web protocols, making it fully compatible with edge runtimes. You can run checks like `check_guidebook_status` or list active guides using `list_guides` directly from edge locations.

You must always call `mcpClient.close()` when your streaming session finishes. This prevents open HTTP connections from hanging in your serverless environment and keeps your execution costs down.

Yes. Vinkius runs this MCP Server in an isolated, zero-trust sandbox. Your event rosters, retrieved via `list_attendees`, and schedule details never leak or persist in the runtime environment.

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