How to Use the Deskpro MCP in Vercel AI SDK

Q: Is my Deskpro customer profile data safe when using this MCP Server?

Absolutely. Tools like getuserprofile run inside isolated, ephemeral V8 sandboxes that destroy themselves after execution. Your customer emails and internal ticket histories are never stored, cached, or used to train models.

Build Next.js support tools where Deskpro ticket updates stream live using the Vercel AI SDK MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deskpro MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time ticket streaming in Next.js

The `list_helpdesk_tickets` tool fetches active customer issues and streams them directly into your React components without annoying page reloads. Your Vercel AI SDK client feeds this data straight into live UI tables, showing ticket status changes as they happen. Instead of making users wait for a full API response, your frontend displays the ticket list incrementally. If a customer asks for open support requests, the agent pulls them instantly and renders the UI cards on the fly.

Live knowledgebase lookups on the Edge

The `get_article_content` tool pulls raw helpdesk articles to answer customer questions inside your Vercel AI SDK chat interface. Because this MCP Server runs on edge-compatible infrastructure, these lookups bypass heavy server roundtrips to keep your chat interface incredibly fast. Your agent reads the article body and summarizes the fix for the user while streaming the response. Users get immediate, accurate answers sourced directly from your Deskpro knowledgebase without staring at a blank screen.

Instant ticket creation via Vercel AI SDK UI

The `create_new_helpdesk_ticket` tool accepts a subject, email, and message from your frontend form to open a support case instantly. Using Vercel AI SDK, your app handles this background creation process while keeping the user informed of the progress live. This direct connection means you don't have to build custom API endpoints or handle complex state management yourself. The MCP Server handles the Deskpro API handshake, letting your UI focus on displaying the newly generated ticket ID.

Setup guide

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

Use streamText along with createMCPClient to pipe the outputs of list_helpdesk_tickets directly to your frontend. The Vercel AI SDK handles the stream, rendering tickets in real-time as they are fetched from your helpdesk.

Yes. This MCP Server runs on Vinkius's V8 sandbox, making it lightweight enough to call from Vercel AI SDK applications deployed on edge runtimes. You avoid cold starts while maintaining access to get_ticket_details.

Vinkius manages the API keys for your helpdesk, exposing a single secure endpoint token. You pass this token into your createMCPClient configuration, allowing the Vercel AI SDK to securely call tools like update_ticket_properties.

The SDK catches the error from the MCP Server tool and allows you to handle it gracefully in your UI. If check_api_health fails, your interface can instantly fallback to a static contact form.

Absolutely. Tools like get_user_profile run inside isolated, ephemeral V8 sandboxes that destroy themselves after execution. Your customer emails and internal ticket histories are never stored, cached, or used to train models.

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