How to Use the Box MCP in AutoGen
Let your AutoGen agents debate, organize, and manage Box files in multi-agent workflows.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Box MCP to AutoGen
Create your Vinkius account to connect Box to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.
Multi-agent consensus via Box MCP Server
The `create_folder` tool lets your AutoGen agents build new directories in Box starting from root "0". Before running this, a manager agent might debate with a security agent to decide where the folder belongs. This collaborative decision-making ensures folders aren't created haphazardly. Once they agree, the agent executes the tool via this MCP Server.
Collaborative sharing and role assignment
The `create_collaboration` tool assigns roles like editor, viewer, or previewer to users on a specific Box folder. In an AutoGen setup, one agent can request access for a user, while another checks permissions before running the tool. This prevents unauthorized sharing. The agents verify the current identity using `get_current_user` before finalizing any collaboration invites.
Automated file cleanup and metadata updates
The `delete_file` tool removes unwanted files from your Box storage. For folders, the agent uses `delete_folder` with the recursive flag set to true if the directory contains other items. Another agent can monitor this process, using `get_file_info` to double-check file sizes and SHA1 hashes before giving the green light to delete. They can also use `update_file` to rename files instead of deleting them.
Set up Box MCP in AutoGen
Prerequisites
- Python 3.10+ installed
-
autogen-ext[mcp]package - Active Vinkius subscription with a valid endpoint token
- 1
Install AutoGen with MCP
Run
pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includesmcp_server_toolsfor stateless tool access. - 2
Fetch tools from the MCP
Call
mcp_server_tools(SseServerParams(url=...))with your Vinkius endpoint. Replace[YOUR_TOKEN_HERE]with your token from cloud.vinkius.com. - 3
Run your agent
Pass the tools to
AssistantAgentand callagent.run(). The agent invokes Box tools and returns structured results.
from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
server_params = SseServerParams(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
tools = await mcp_server_tools(server_params)
agent = AssistantAgent(
name="Box_assistant",
model_client=OpenAIChatCompletionClient(model="gpt-4o"),
tools=tools,
)
result = await agent.run("List recent Box data")
print(result.messages[-1].content) Prerequisites
- Python 3.10+ installed
-
autogen-ext[mcp]+autogen-agentchat - Active Vinkius subscription with a valid endpoint token
- 1
Install dependencies
Same packages as above.
McpWorkbenchis ideal when your agent needs stateful sessions across multiple tool calls. - 2
Use McpWorkbench as context manager
Wrap your agent in
async with McpWorkbench(...)to maintain shared state and resources. The workbench manages the full MCP session lifecycle. - 3
Run with workbench
Pass
workbench=workbenchto your agent. State is preserved across multiple tool calls within the same session.
from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
server_params = SseServerParams(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
async with McpWorkbench(server_params) as workbench:
agent = AssistantAgent(
name="Box_assistant",
model_client=OpenAIChatCompletionClient(model="gpt-4o"),
workbench=workbench,
)
result = await agent.run("List recent Box data")
print(result.messages[-1].content) 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.
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 AutoGen
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Box MCP today
We host it, we monitor it, we maintain it. You just paste one token.