How to Use the Box MCP in LlamaIndex

Q: How do I configure LlamaIndex to connect with Box?

Install llama-index-tools-mcp and initialize BasicMCPClient with your Vinkius endpoint. Convert it using McpToolSpec and call totoollistasync() to register the tools.

Q: Can I index Box metadata into a vector store with LlamaIndex?

Yes. You can fetch file metadata using getfileinfo and ingest the results directly into your document store. This grounds your queries in actual, live file properties.

Q: How does LlamaIndex handle Box folder hierarchies?

LlamaIndex uses listfolderitems starting from folder ID "0" to map out your file paths. This allows your RAG application to understand the relationship between directories and nested files.

Q: Does this MCP Server support asynchronous execution?

Yes. You can load these tools asynchronously using totoollistasync(). This ensures your LlamaIndex pipelines run concurrently without blocking your main event loop.

Index Box files into LlamaIndex vector stores to ground your RAG applications in real-time document data.

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 LlamaIndex

Create your Vinkius account to connect Box to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Box folder structures for LlamaIndex RAG

The `list_folder_items` tool pulls names, sizes, and modified dates from root folder "0" or any subfolder, exposing them to your MCP client. LlamaIndex takes this raw directory structure and indexes it, allowing your agent to navigate file paths semantically. By feeding this metadata into your index, your RAG pipeline knows where files live before reading them. Your agent uses `get_folder_info` to keep its knowledge base synchronized with your actual cloud hierarchy.

Targeted document search and indexing

The `search_content` tool targets specific file formats like PDF, DOCX, and XLSX. Your LlamaIndex pipeline uses this MCP Server to retrieve deep text matches and index only the relevant chunks. Instead of pulling entire directories, the agent uses `get_file_info` to check file sizes first. This keeps your vector database lean and prevents you from indexing stale or massive documents.

Enterprise user sync for context-aware RAG

The `list_users` tool retrieves your enterprise user directory directly into LlamaIndex. Your application can map document permissions and user context to ensure the right people query the right files. Combining this with `get_folder_collaborations` lets your index filter search results dynamically. Your agent checks who has access to a folder before serving its contents to a user query.

Setup guide

Set up Box MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Box MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Box tools.",
)
response = await agent.run("List recent Box data")

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 LlamaIndex

Install `llama-index-tools-mcp` and initialize `BasicMCPClient` with your Vinkius endpoint. Convert it using `McpToolSpec` and call `to_tool_list_async()` to register the tools.

Yes. You can fetch file metadata using `get_file_info` and ingest the results directly into your document store. This grounds your queries in actual, live file properties.

LlamaIndex uses `list_folder_items` starting from folder ID "0" to map out your file paths. This allows your RAG application to understand the relationship between directories and nested files.

Yes. You can load these tools asynchronously using `to_tool_list_async()`. This ensures your LlamaIndex pipelines run concurrently without blocking your main event loop.

This MCP connection runs inside a zero-trust, ephemeral V8 sandbox. Your enterprise user lists and collaborator data retrieved via `list_users` are processed in memory and never persisted.

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