How to Use the Box MCP in OpenAI Agents SDK

Q: How do I connect the Box MCP Server to my OpenAI Agents SDK pipeline?

Instantiate MCPServerStreamableHttp with the Vinkius endpoint URL. Pass this server instance in the mcpservers list when initializing your Agent, which automatically registers the MCP tools.

Q: Can my OpenAI Agents SDK agent search inside PDF files on Box?

Yes, the searchcontent tool supports deep content indexing. Your agent can search for text inside PDFs, Word documents, and spreadsheets by passing the file extension filter.

Q: What is the default parent directory when creating a folder?

The createfolder tool defaults to the root folder, which has an ID of "0". If you want to nest folders, simply pass a specific parent folder ID instead.

Build production OpenAI Agents SDK systems that safely manage Box folders and files with built-in execution guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Box to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Structure files using OpenAI Agents SDK

The `create_folder` and `list_folder_items` tools let your agent map out and build directory structures in Box. Your Python agents can inspect the root directory using ID "0" to see what files exist, then build out new directories instantly based on user prompts. Because this runs within the OpenAI Agents SDK, you can set up strict guardrails to inspect the path before creating anything. If an agent tries to modify a folder it shouldn't, your system intercepts the call before it hits the network.

Deep content search with MCP Server tools

The `search_content` tool executes deep text queries inside documents, filtering results by PDF, Word, or Excel formats. Your agent can scan through hundreds of contracts or financial sheets without downloading them, extracting exact answers from deep within the file contents. This MCP Server integration allows specialized OpenAI agents to pass execution context back and forth. One agent can locate the files, while another parses the metadata, all tracked directly on your OpenAI developer dashboard.

Audit folder access and collaborations

The `get_folder_collaborations` and `list_users` tools expose who has access to specific enterprise assets. Your agent checks who is shared on a sensitive directory and cross-references them against your internal user directory. This setup prevents unauthorized file sharing by letting your agent automatically flag external emails. You get a clean audit trail of your Box permission state without writing custom API wrapper logic.

Setup guide

Set up Box MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Box tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Box tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Box tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Box Agent",
            instructions="You have access to Box tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Instantiate `MCPServerStreamableHttp` with the Vinkius endpoint URL. Pass this server instance in the `mcp_servers` list when initializing your Agent, which automatically registers the MCP tools.

Yes, the `search_content` tool supports deep content indexing. Your agent can search for text inside PDFs, Word documents, and spreadsheets by passing the file extension filter.

Yes, it works natively with agent handoffs. You can have a search agent locate files using `search_content`, then hand off the file ID to a security agent that checks permissions.

The `create_folder` tool defaults to the root folder, which has an ID of "0". If you want to nest folders, simply pass a specific parent folder ID instead.

Vinkius runs the server in an isolated V8 sandbox, preventing any persistent storage of your enterprise data. Your file metadata and collaboration lists are only processed in memory during the active API call, keeping your corporate directory private.

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