How to Use the Box MCP in LangChain

Q: How do I add the Box MCP Server to my LangChain project?

Install langchain-mcp-adapters and langgraph via pip. Instantiate the MultiServerMCPClient pointing to the Vinkius URL, call client.gettools(), and pass them straight to createagent.

Q: Can LangChain agents search inside files on Box?

Yes. The agent calls searchcontent to search inside DOCX, PDF, and XLSX files. It filters by file extensions or folder IDs, returning precise results back to your chain.

Build LangChain reasoning loops that search and organize your Box files based on live agent decisions.

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

Chained Box folder creation and sorting

The `create_folder` tool lets your LangChain agent build directory structures on the fly, starting from the root folder ID "0". Your agent evaluates previous run outputs, decides if a directory exists, and spins up new ones when needed. You can feed the resulting folder ID directly into `list_folder_items` inside a single LangGraph run. This turns manual file management into a predictable, automated sequence where the output of one step guarantees the success of the next.

Deep content search in LangChain pipelines

The `search_content` tool allows your agent to scan inside PDF, DOCX, and XLSX files. LangChain pipelines use this to locate specific enterprise documents without wasting tokens on irrelevant files. You get a clean, validated data flow from this MCP Server that feeds directly into your downstream LLM prompt chains. Once the search finds the right target, the agent runs `get_file_info` to inspect file size and modification dates.

Audit collaborations with LangSmith tracing

The `get_folder_collaborations` tool exposes who has access to your sensitive directories. Your LangChain agent can pull this list and cross-reference it with your internal directory standards. Because every MCP tool call is monitored, LangSmith logs the exact latency and inputs of `list_users` during the execution. You see exactly when and why your agent verified user access.

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-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 `langgraph` via pip. Instantiate the `MultiServerMCPClient` pointing to the Vinkius URL, call `client.get_tools()`, and pass them straight to `create_agent`.

Yes. The agent calls `search_content` to search inside DOCX, PDF, and XLSX files. It filters by file extensions or folder IDs, returning precise results back to your chain.

Yes, it is designed for that. You can aggregate this server alongside other tools using the `MultiServerMCPClient` to let your agents combine cloud storage tasks with database queries in one run.

The agent uses folder ID "0" as the root default. When calling `list_folder_items` or `create_folder`, passing "0" tells the server to start at your main directory level.

Vinkius runs the MCP adapter in a secure V8 Isolate sandbox. Your files, folder metadata, and collaborator lists are never stored or used to train models, keeping your enterprise data completely isolated.

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