How to Use the Hullo MCP in Vercel AI SDK

Q: How do I stream Hullo member directories using the Vercel AI SDK?

You call mcpClient.tools() to get the Hullo tools and pass them into streamText. Your frontend will then render the results of listmembers in real-time as the data streams in.

Q: How does the Vercel AI SDK handle Hullo chat tools like sendmessage?

The SDK routes the sendmessage tool through your agent, allowing it to post updates directly to your workspace members. The response streams back to confirm delivery immediately.

Stream Hullo coworking member profiles and live chat feeds directly to your React app with 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 Hullo MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render live member directories in your React frontend

The `list_members` tool lets your MCP client fetch the entire active directory of your coworking space and stream it straight to the browser. Instead of waiting for a bulky REST payload to resolve behind a spinner, your Vercel AI SDK client renders each member card on screen as the data arrives. When a community manager needs to inspect a specific profile, the agent calls `get_member` to pull contact info and check-in history. This keeps your Next.js dashboard fast and responsive, giving your staff instant access to member profiles.

Feed real-time chat feeds into streaming UI components

The `list_conversations` tool feeds real-time community chat directly into your Edge Functions. Run this Hullo MCP Server on Edge to handle community chat without slowing down your main application database. When an operator asks to see recent activity, the agent invokes the tool and streams the active threads directly into your UI. If an urgent issue pops up, your custom interface can trigger `get_conversation` to fetch the transcript or use `send_message` to post an immediate announcement. The Vercel AI SDK handles the network plumbing so your community team can chat with members in real-time.

Onboard new coworkers dynamically using Vercel AI SDK

The `create_member` tool lets you build a custom self-service kiosk that lets new arrivals register themselves. The agent takes their raw inputs and instantly adds them to your local database. This setup bypasses complex backend routing because the MCP tool results plug directly into your UI components. Your front-end handles the onboarding flow while Hullo manages the actual workspace records.

Setup guide

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

You call `mcpClient.tools()` to get the Hullo tools and pass them into `streamText`. Your frontend will then render the results of `list_members` in real-time as the data streams in.

Yes, this MCP Server is fully compatible with Edge runtimes. You can query `get_member` and stream the response to the user within milliseconds.

The SDK routes the `send_message` tool through your agent, allowing it to post updates directly to your workspace members. The response streams back to confirm delivery immediately.

No, the SDK manages the UI state for you. When your agent calls `list_conversations`, the data feeds directly into your React hooks.

All member profiles and chat logs are processed inside an isolated MCP sandbox environment. Your credentials and member records never touch external servers, keeping your space's data locked down.

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