How to Use the Help Scout MCP in Vercel AI SDK

Q: How do I connect the Help Scout MCP to Vercel AI SDK?

Install @ai-sdk/mcp. Use createMCPClient with your endpoint URL, call mcpClient.tools(), and pass the result to your streamText function.

Q: Can Vercel AI SDK stream Help Scout conversation notes?

Yes. When your agent calls getconversation, the SDK streams the entire thread history directly into your React components in real time.

Q: How do I filter Help Scout tickets in my Next.js app?

Bind searchconversations to a UI input field. The agent will execute the query and stream the matching Help Scout tickets back to the frontend.

Q: Data privacy: What customer info does this server access?

The getcustomer tool pulls exact names, email addresses, and location data from your help desk. Vinkius runs this connection in an ephemeral V8 Isolate, meaning your client streams the PII into the React UI and we destroy the state immediately.

Build live customer support dashboards in React using Vercel AI SDK to stream Help Scout data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Help Scout MCP to Vercel AI SDK

Create your Vinkius account to connect Help Scout 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 Help Scout with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live support queues

Vercel AI SDK pushes Help Scout data directly to your frontend. You don't need loading spinners when pulling active tickets. The Help Scout MCP integration allows you to call `list_conversations` and watch the queue populate in your React components instantly. If a user searches for a specific issue, your agent fires `search_conversations`. The results stream straight into the UI, giving your support team immediate context without hitting refresh. You build the interface, and the AI client handles the data transport.

Render customer profiles on the fly

Support reps need context fast. Your Next.js app can trigger `get_customer` to pull exact profile details while the user types. The agent streams this data into a side panel, keeping your team focused on the actual conversation instead of hunting through tabs. You can also pull satisfaction scores via `list_customer_ratings`. The client executes the tool in the background and pipes the text right into your Svelte or Vue interface. Data appears the exact millisecond the Help Scout API returns it.

Update tickets from the Vercel AI SDK MCP Server

Reading data is only half the job. Your custom interface needs to close loops. Use `update_convo_status` to close tickets the moment an agent finishes a task directly from your custom web app. Team collaboration happens instantly too. Trigger `create_convo_note` to drop private summaries into the thread. The AI client handles the HTTP transport, meaning your frontend stays fast and responsive while the server does the heavy lifting.

Setup guide

Set up Help Scout 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 Help Scout 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 Help Scout 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 Help Scout. 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 Help Scout 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 Help Scout MCP in Vercel AI SDK

Install `@ai-sdk/mcp`. Use `createMCPClient` with your endpoint URL, call `mcpClient.tools()`, and pass the result to your `streamText` function.

Yes. When your agent calls `get_conversation`, the SDK streams the entire thread history directly into your React components in real time.

Bind `search_conversations` to a UI input field. The agent will execute the query and stream the matching Help Scout tickets back to the frontend.

Yes. The transport layer relies on standard HTTP, meaning you can run these tools safely in Edge environments without Node.js dependencies.

The `get_customer` tool pulls exact names, email addresses, and location data from your help desk. Vinkius runs this connection in an ephemeral V8 Isolate, meaning your client streams the PII into the React UI and we destroy the state immediately.

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