How to Use the Box MCP in Vercel AI SDK

Q: How does Vercel AI SDK manage large Box file deletions?

The SDK sends the request to the deletefile tool. For folders, the model sets the recursive parameter to true, ensuring the entire directory tree gets wiped without leaving orphaned files behind.

Stream real-time Box folder structures directly into your frontend using this MCP Server and 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 Box MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time UI updates with Vercel AI SDK

The `list_folder_items` tool lets your app read directory contents directly from Box. Because you are using the Vercel AI SDK, these file lists stream straight to your React or Next.js frontend without making the user stare at a loading spinner. When users request a directory view, the SDK calls `get_folder_info` and updates the layout piece by piece. You get a fast, responsive interface that feels like a local file explorer instead of a slow cloud sync tool.

Secure folder creation and file management

The `create_folder` tool lets your client build new directories on the fly. It uses parent ID "0" to start at the root, giving you a clean slate for organizing user uploads. If a user decides to clean up their workspace, the `delete_folder` tool handles the removal. Just set the recursive flag to true, and the server wipes the target folder and its contents in one clean step.

Live Box search inside your streaming application

The `search_content` tool finds files and directories when your user does not know the exact IDs. This MCP Server feeds those search results directly into the Vercel AI SDK streaming text function. Once the file is found, your agent can trigger `get_file_info` to show the size, version, and SHA1 hash. Users see these file details populate their screen instantly as the model finds them.

Setup guide

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

Install the core packages and initialize the client using the Vinkius HTTP endpoint. Pass the tools directly into your text generation function, then close the client connection when the request finishes.

Yes. The SDK supports OAuth providers, meaning you can authenticate individual users before executing actions like `get_current_user` to verify their identity.

The SDK sends the request to the `delete_file` tool. For folders, the model sets the recursive parameter to true, ensuring the entire directory tree gets wiped without leaving orphaned files behind.

Yes, the integration runs perfectly on Vercel Edge Functions. The lightweight HTTP transport ensures minimal latency when pulling metadata or updating file descriptions.

Every request runs through a sandboxed V8 isolate on Vinkius. Your file hashes, collaborator emails, and folder paths are never stored, and the server only touches the specific directories you authorize.

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