How to Use the Helpshift MCP in Vercel AI SDK

Q: How do I connect Helpshift to Vercel AI SDK?

Install @ai-sdk/mcp and initialize it with createMCPClient. You pass the HTTP transport URL pointing to your Helpshift MCP server. Call mcpClient.tools() to expose the operations to your streaming functions.

Q: Can Vercel AI SDK create Helpshift tickets?

Yes. Your agent calls the createissue tool with the required JSON payload. It needs the app ID, a title, and the issue body.

Q: How do I load Helpshift FAQs into a Vercel AI SDK chat?

Use the listfaqs tool. Your agent grabs the published articles and streams the relevant answers back to the user. You can also map categories using listfaqsections.

Stream Helpshift support tickets and FAQs directly into your React UI with 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 Helpshift MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Support Queue Streaming

The `list_issues` tool pulls your current support queue directly into your Vercel AI SDK application. Support volume spikes happen fast. You can monitor urgent cases as they arrive without forcing users to refresh a dashboard. Your edge functions fetch the data and stream it straight to the frontend. Deep dives require context. Calling `get_issue_details` streams the exact ticket history into your React UI. Customers see the AI reading their past interactions in real-time. This completely eliminates the wait for a loading spinner to finish.

Helpshift MCP Server Ticket Creation

Triggering `create_issue` generates new support tickets from user prompts. You pass the app ID, title, and body as a JSON string. The agent handles the formatting. This means your Next.js frontend can turn a frustrated user's chat message into a tracked issue instantly. Following up is just as fast. The `add_issue_message` tool appends new context to the ticket. You just pass the message details in the body. The UI updates live as the AI confirms the addition.

Instant Knowledge Retrieval

The `list_faqs` tool grabs your published articles and streams the answers back to the user. Nobody wants to dig through a help center. Your agent reads the user's problem, queries the database, and types out the exact fix. Organizing that data takes one step. Calling `list_faq_sections` maps your categories. The AI understands your support structure and navigates the documentation exactly like a human agent would.

Setup guide

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

Install `@ai-sdk/mcp` and initialize it with `createMCPClient`. You pass the HTTP transport URL pointing to your Helpshift MCP server. Call `mcpClient.tools()` to expose the operations to your streaming functions.

Yes. Your agent calls the `create_issue` tool with the required JSON payload. It needs the app ID, a title, and the issue body.

The server itself returns JSON, but Vercel AI SDK streams those tool results to your frontend. Users watch the ticket details populate instantly.

Use the `list_faqs` tool. Your agent grabs the published articles and streams the relevant answers back to the user. You can also map categories using `list_faq_sections`.

Your MCP Server isolates support tickets and user profiles inside a V8 sandbox. Vinkius handles the ephemeral connection, meaning your API keys stay secure. The agent only reads the specific ticket payloads it needs for the current prompt.

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