How to Use the Desku.io MCP in Vercel AI SDK

Q: How do I connect Desku.io to the Vercel AI SDK?

Run npm install ai @ai-sdk/mcp in your terminal. Initialize the connection using createMCPClient({ transport: { type: "http", url: "..." } }). Then pass the results of mcpClient.tools() into your streamText function.

Q: Can the Vercel AI SDK stream Desku.io ticket updates?

Yes. When the model calls MCP tools like getticket, the result streams straight to your React or Svelte UI. Users watch the data appear in real time.

Q: Does this MCP Server support OAuth for customer authentication?

Yes, it does. You can configure the authProvider in your client setup. This ensures the model only accesses records the current user is allowed to see.

Build real-time customer support interfaces by streaming Desku.io data directly to your frontend 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 Desku.io MCP to Vercel AI SDK

Create your Vinkius account to connect Desku.io 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 Desku.io with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Support Dashboards

Your React application needs live ticket data without making users stare at loading spinners. Passing the `list_tickets` and `get_ticket` tools to your Vercel AI SDK setup streams that exact information straight to the client. The UI updates instantly as the model processes the support queue. You don't have to write custom polling logic to check for new messages. When a user asks about their issue, the model calls `list_conversations` and streams the reply history right into the chat component. Edge functions handle the heavy lifting while keeping the frontend fast.

Connect Vercel AI SDK to Desku.io

Giving your AI client write access means users can manage their own requests. They type a complaint into your Next.js app, and the model triggers `create_ticket` behind the scenes. It grabs the user's context using `get_customer` to ensure the new record has the right metadata attached. Updating status happens just as fast. If a customer confirms their bug is fixed, the agent runs `update_ticket` and streams a confirmation message back. You get a fully interactive support portal with zero custom API boilerplate.

Route Complex Inquiries Instantly

Sometimes an automated reply isn't enough to solve a problem. Your AI needs to know who is available to help before escalating an issue. By exposing `list_agents`, the MCP Server lets the model check the active roster and assign the case to a real person. Adding a note for that human agent is simple. The model executes `create_conversation` to drop a private summary into the thread. The customer sees a smooth transition, and your support team gets all the context they need.

Setup guide

Set up Desku.io 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 Desku.io 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 Desku.io 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 Desku.io. 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 Desku.io 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 Desku.io MCP in Vercel AI SDK

Run `npm install ai @ai-sdk/mcp` in your terminal. Initialize the connection using `createMCPClient({ transport: { type: "http", url: "..." } })`. Then pass the results of `mcpClient.tools()` into your `streamText` function.

Yes. When the model calls MCP tools like `get_ticket`, the result streams straight to your React or Svelte UI. Users watch the data appear in real time.

The SDK catches the error and surfaces it in the tool invocation result. You can handle the fallback in your application code or prompt the model to try the request again.

Yes, it does. You can configure the `authProvider` in your client setup. This ensures the model only accesses records the current user is allowed to see.

Vinkius runs this integration in a V8 Isolate Sandbox. Your customer email addresses, chat histories, and support metadata never touch persistent storage. The container spins up, handles the request, and vanishes immediately after execution.

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