How to Use the Box MCP in CrewAI

Q: How does CrewAI handle Box permission errors?

If an agent attempts createcollaboration and fails due to permissions, the moderator agent catches the error and can escalate the issue to a human admin.

Deploy specialized agent crews to manage Box files, folders, and permissions autonomously using this MCP Server in CrewAI.

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 CrewAI

Create your Vinkius account to connect Box to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative file organization with CrewAI

The `create_folder` tool lets your agent team build organized directory structures on demand. In a CrewAI setup, one agent can plan the folder hierarchy while another agent executes the creation. By using parent ID "0" for the root, the crew keeps the top level clean. The agents coordinate using shared memory to ensure they never create duplicate directories.

Automated permission auditing using this MCP Server

The `get_folder_info` tool retrieves creator details, parent directories, and modified dates. This MCP Server gives your auditing crew the exact data they need to evaluate security settings. A researcher agent can run `list_folder_items` to map the workspace, while a compliance agent uses `create_collaboration` to adjust user roles to the correct access levels.

Autonomous content discovery and maintenance

The `search_content` tool locates files across your entire account when IDs are missing. Your CrewAI agents use this tool to track down misplaced documents without human help. Once located, a maintenance agent can use `update_file` to fix file names or update descriptions. If the files are marked as obsolete, a coordinator agent triggers `delete_file` to purge them.

Setup guide

Set up Box MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Box tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Box Analyst",
    goal="Access and analyze Box data via MCP.",
    backstory="Expert analyst with direct Box access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Box transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Box Analyst",
        goal="Access and analyze Box data via MCP.",
        backstory="Expert analyst with direct Box access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Box transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the Vinkius HTTP endpoint URL directly into your CrewAI agent definition. The framework automatically registers the tools and makes them available to your specialized agents.

Yes. The agents share context and memory, allowing one agent to find a file using `search_content` and another agent to read it with `get_file_info`.

If an agent attempts `create_collaboration` and fails due to permissions, the moderator agent catches the error and can escalate the issue to a human admin.

The framework supports stdio, SSE, and Streamable HTTP. Most developers prefer the HTTP transport for cloud deployments because it simplifies credential management.

Every API call runs inside a secure, ephemeral V8 isolate. Your file names, folder structures, and sharing permissions are never exposed or stored outside your execution environment.

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