How to Use the Helpwise MCP in Vercel AI SDK

Q: How do I connect the Helpwise MCP Server to my Vercel AI SDK app?

Install @ai-sdk/mcp and ai, then call createMCPClient with your Vinkius HTTP URL. Pass the tools from mcpClient.tools() directly into streamText and remember to call mcpClient.close() when the execution finishes.

Q: How does the Helpwise MCP Server handle user authentication in Vercel AI SDK?

You use the authProvider configuration inside createMCPClient to manage OAuth tokens. This lets your app securely execute actions like sendemail on behalf of individual support agents.

Q: What is the best way to list team members in this setup?

Run listteammembers to fetch the agent directory. The Vercel AI SDK can then map these IDs to assign conversations or display agent names in your custom support dashboard.

Build live customer support views where your Vercel AI SDK app streams Helpwise conversation updates straight to the screen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Helpwise MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Helpwise mailboxes live with Vercel AI SDK

The `list_mailboxes` tool fetches your active shared mailboxes so your application can render them immediately. Instead of waiting for a full page reload, the client streams the mailbox list directly into your React or Next.js frontend components. Once a mailbox is selected, `list_conversations` pulls the active message threads. The Vercel AI SDK handles this on Edge Functions, rendering incoming customer queries as they arrive without keeping your users waiting behind a spinner.

Respond to threads using streaming text tools

The `send_email` tool lets your app dispatch replies directly from the user interface. Your agent drafts the response and fires it off using this MCP Server, while your frontend shows the exact status of the outgoing message in real-time. To keep the UI updated, `get_conversation_details` pulls the updated thread history immediately after sending. This keeps the client state in sync with Helpwise without forcing manual polling loops.

Build and update customer profiles on the fly

The `create_contact` tool registers new customer details right from the streaming chat interface. When a user provides their details, this MCP Server invokes this tool to store the name and email address instantly. You can also run `list_contacts` to check existing customer records before creating duplicates. This ensures your UI always shows accurate, clean records from the Helpwise database during live interactions.

Setup guide

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

Install `@ai-sdk/mcp` and `ai`, then call `createMCPClient` with your Vinkius HTTP URL. Pass the tools from `mcpClient.tools()` directly into `streamText` and remember to call `mcpClient.close()` when the execution finishes.

Yes, the MCP client is fully compatible with Edge runtimes. It uses standard HTTP transports to invoke `get_conversation_details` and stream the email body to your Next.js frontend without cold starts.

You use the `authProvider` configuration inside `createMCPClient` to manage OAuth tokens. This lets your app securely execute actions like `send_email` on behalf of individual support agents.

Run `list_team_members` to fetch the agent directory. The Vercel AI SDK can then map these IDs to assign conversations or display agent names in your custom support dashboard.

Your actual email payloads and contact records never touch third-party databases. Vinkius runs the MCP Server in an isolated V8 sandbox, routing data directly from the Helpwise API to your SDK app over encrypted HTTPS tunnels.

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