How to Use the Box MCP in LangChain

Q: How do I connect the Box MCP Server to my LangChain agents?

Install langchain-mcp-adapters and use the MultiServerMCPClient pointing to the Vinkius MCP endpoint. Pass the retrieved tools directly to your agent executor or LangGraph workflow.

Q: Can LangChain automatically share a newly created Box folder?

Yes. Your agent first runs createfolder to generate the directory, then passes that folder ID to createcollaboration along with the user's email and role.

Q: How does LangChain handle empty folder deletion in Box?

The agent checks folder contents with listfolderitems. If it needs to wipe a directory, it calls deletefolder with the recursive parameter set to true.

Q: Can I trace Box metadata updates in LangSmith?

Absolutely. Every time your agent uses updatefile to rename a file or change its description, LangSmith logs the exact inputs, outputs, and latency.

Let your LangChain agents organize, share, and search Box files directly inside your LLM chains.

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 LangChain

Create your Vinkius account to connect Box to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run deep file searches inside LangChain chains

The `search_content` tool lets your agent find files and folders on Box without needing hardcoded IDs. When a user asks about a specific document, your agent queries the Box API, grabs the metadata with `get_file_info`, and passes it to the next step in your chain. This setup turns your LangChain runs into active file locators. You don't have to copy-paste file hashes; the model resolves them dynamically using this MCP Server.

Automated folder structures and collaboration

The `create_folder` tool builds new directories in Box, using parent ID "0" to start right at the root. From there, the agent invokes `create_collaboration` to invite teammates by email, assigning roles like editor or viewer automatically. By chaining these steps in LangGraph using an MCP client, you build self-managing workspaces. If a project kicks off, your agent spins up the directory and shares it with the team in one run.

Metadata extraction and cleanup in LangChain

The `get_folder_info` tool retrieves creator names, modification dates, and parent structures directly into your LLM context. If your agent detects empty or outdated folders, it runs `delete_folder` with the recursive flag set to true to clear out the junk. LangSmith traces every single call, so you see exactly when your agent checks `get_file_info` or updates metadata using `update_file`. It keeps your cloud storage clean without manual oversight.

Setup guide

Set up Box MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Box tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "box-alternative-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Box transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` pointing to the Vinkius MCP endpoint. Pass the retrieved tools directly to your agent executor or LangGraph workflow.

Yes. Your agent first runs `create_folder` to generate the directory, then passes that folder ID to `create_collaboration` along with the user's email and role.

The agent checks folder contents with `list_folder_items`. If it needs to wipe a directory, it calls `delete_folder` with the recursive parameter set to true.

Absolutely. Every time your agent uses `update_file` to rename a file or change its description, LangSmith logs the exact inputs, outputs, and latency.

Yes, your Box files, folders, and collaboration details are protected by Vinkius's zero-trust V8 sandbox. The server only handles your active session tokens, keeping your enterprise content isolated and secure.

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