How to Use the BOSSDesk MCP in Vercel AI SDK

Q: How do I load BOSSDesk tickets in a Vercel AI SDK app?

Install the @ai-sdk/mcp package and initialize the MCP client with your Vinkius endpoint. Pass the listtickets tool directly into streamText to let your agent fetch and display active support issues.

Q: Can Vercel AI SDK update BOSSDesk tickets in real-time?

Yes, the SDK can call updateticket and addticketnote mid-stream. This allows your agent to write comments and change ticket statuses while streaming the text response to your user.

Q: Is there a way to verify physical locations before creating a ticket?

You can configure your agent to query listlocations before calling createticket. This ensures every new issue has an accurate office location attached from the start.

Stream BOSSDesk tickets and asset states directly into your React components using the Vercel AI SDK without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BOSSDesk MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream BOSSDesk tickets to Vercel AI SDK UI

Your Next.js app can now render IT support tickets live using the BOSSDesk MCP Server, mapping physical locations and assets directly to active issues. Instead of making users wait for API responses, this MCP Server pushes BOSSDesk ticket payloads directly into your Vercel AI SDK UI components. As your user types a complaint, the SDK calls `create_ticket` or updates an existing issue using `update_ticket` to show the update on the screen immediately.

Inspect BOSSDesk assets on the edge

Run asset lookups inside Edge Functions without database bottlenecks using this BOSSDesk inventory tool. The SDK triggers `get_asset` or `list_assets` to pull serial numbers and hardware details the second an agent identifies a hardware issue. This setup keeps your Next.js frontend fast because the MCP integration avoids heavy server-side roundtrips to fetch BOSSDesk assets. Your client-side components grab inventory data directly from the server stream.

Interactive user routing via Vercel AI SDK

Resolve employee issues by letting your agent query BOSSDesk user profiles in real-time. The SDK uses `get_user` and `list_users` to match incoming messages with specific employees and their office locations. This MCP Server setup allows you to build a custom admin dashboard where your agent automatically assigns tickets to the right physical desk using `list_locations` based on the user's profile.

Setup guide

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

Install the `@ai-sdk/mcp` package and initialize the MCP client with your Vinkius endpoint. Pass the `list_tickets` tool directly into `streamText` to let your agent fetch and display active support issues.

Yes, the SDK can call `update_ticket` and `add_ticket_note` mid-stream. This allows your agent to write comments and change ticket statuses while streaming the text response to your user.

The server runs in a secure sandbox hosted by Vinkius, which connects over HTTP. Your Vercel AI SDK code runs on the edge and communicates with the server via lightweight JSON-RPC.

You can configure your agent to query `list_locations` before calling `create_ticket`. This ensures every new issue has an accurate office location attached from the start.

All ticket descriptions, hardware serial numbers, and employee profiles are protected inside an isolated V8 sandbox on Vinkius. The MCP Server keeps your API keys secure on your backend, so they never touch the client browser.

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