How to Use the BoxHero MCP in CrewAI

Q: How do I configure CrewAI agents to use BoxHero?

Pass your Vinkius HTTP URL to the mcps list to register the MCP Server. Your agents will automatically discover and use tools like listitems during their tasks.

Q: Can I restrict certain CrewAI agents from deleting BoxHero items?

Yes, use MCPServerHTTP with a toolfilter to exclude deleteitem from specific agents. This ensures only your manager agent can remove inventory.

Deploy a collaborative team of CrewAI agents to manage your BoxHero warehouse operations autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BoxHero MCP to CrewAI

Create your Vinkius account to connect BoxHero 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 BoxHero with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative warehouse auditing via CrewAI

The `list_items` tool gives your CrewAI auditing team a complete view of your warehouse stock. A research agent pulls the inventory list, while an analyst agent flags low-stock items for reordering. Once the team identifies shortages, a manager agent calls `create_transaction` to log incoming orders. The agents share context dynamically, ensuring no double-ordering happens.

Multi-agent storage optimization MCP Server

The `list_locations` tool allows your logistics crew to analyze space utilization across your facilities. One agent maps the layout while another checks item dimensions to find the best storage spots. The crew then uses `update_item` to assign products to their new optimal locations. This keeps your physical warehouse organized without requiring human planners.

Autonomous transaction reconciliation

The `list_transactions` tool lets your finance crew reconcile physical shipments with digital logs. The crew cross-references your shipping invoices against recorded stock-in and stock-out events. If the agents spot a discrepancy, they run `get_item` to inspect the product's history. They draft an escalation report for your team, attaching the exact transaction IDs.

Setup guide

Set up BoxHero 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 BoxHero tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent BoxHero 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="BoxHero Analyst",
        goal="Access and analyze BoxHero data via MCP.",
        backstory="Expert analyst with direct BoxHero access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent BoxHero 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 BoxHero. 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 BoxHero 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 BoxHero MCP in CrewAI

Pass your Vinkius HTTP URL to the `mcps` list to register the MCP Server. Your agents will automatically discover and use tools like `list_items` during their tasks.

Yes, use `MCPServerHTTP` with a `tool_filter` to exclude `delete_item` from specific agents. This ensures only your manager agent can remove inventory.

CrewAI's shared memory allows agents to pass the results of the MCP Server's `list_transactions` tool to each other. The analyst agent reads the ledger, and the reporting agent writes the final audit.

We recommend HTTP or SSE for CrewAI setups. The framework handles the connection lifecycle, letting your agents query MCP Server tools synchronously during their runs.

All physical stock details and transaction histories remain within your local execution environment. Vinkius acts as a zero-trust proxy for the MCP Server, meaning your credentials never touch external LLM training loops.

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