How to Use the Box MCP in LlamaIndex

Q: How do I connect this MCP Server to LlamaIndex?

Install llama-index-tools-mcp and initialize the BasicMCPClient. Convert the server tools into a tool spec and pass them to your LlamaIndex agent to start indexing.

Q: Can LlamaIndex search Box folders without knowing the folder ID?

Yes. The agent uses searchcontent to find files and folders by name or keyword, then calls getfileinfo to retrieve the target IDs.

Q: How does LlamaIndex handle recursive folder deletion in Box via this MCP Server?

If your index needs to remove stale data, the agent calls deletefile or deletefolder. To delete non-empty folders, it sets the recursive flag to true.

Q: Can LlamaIndex verify the current Box user identity?

Yes. The agent calls getcurrentuser to verify who is running the pipeline before exposing sensitive files or modifying directory structures.

Index Box folders directly into LlamaIndex vector stores for grounded RAG applications.

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

Map Box directory structures for LlamaIndex RAG

The `list_folder_items` tool reads all items within a Box directory, using ID "0" to start scanning from the root. Your LlamaIndex agent uses this list to find documents, fetching specific metadata like size and SHA1 hashes with `get_file_info`. This live metadata feeds into your semantic index. Instead of guessing, your agent queries real-time directory states directly through this MCP Server.

Search and ground answers with Box content

The `search_content` tool queries your Box account for relevant files when a user's query doesn't match known IDs. The agent retrieves the file details, downloads the content, and indexes it to prevent LLM hallucinations. By grounding your queries in actual Box metadata, you get accurate answers. The agent knows exactly who modified a file and when, thanks to `get_folder_info`.

Maintain and update Box metadata via LlamaIndex

The `update_file` tool changes file names and descriptions directly from your LlamaIndex agent conversations. If the agent notices a document is mislabeled during indexing, it corrects the metadata instantly. You can also manage access during index updates. The agent uses `create_collaboration` to grant viewer or editor roles to users who need access to the indexed files.

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 the `BasicMCPClient`. Convert the server tools into a tool spec and pass them to your LlamaIndex agent to start indexing.

Yes. The agent uses `search_content` to find files and folders by name or keyword, then calls `get_file_info` to retrieve the target IDs.

If your index needs to remove stale data, the agent calls `delete_file` or `delete_folder`. To delete non-empty folders, it sets the recursive flag to true.

Yes. The agent calls `get_current_user` to verify who is running the pipeline before exposing sensitive files or modifying directory structures.

All Box folder structures and file metadata are processed in an ephemeral V8 sandbox using our secure MCP setup. Vinkius handles authentication securely, ensuring no persistent storage of your enterprise file details.

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