How to Use the CartonCloud MCP in CrewAI

Q: Can I restrict which CartonCloud tools a CrewAI agent can use?

You can use the MCPServerHTTP class and apply a toolfilter. This allows you to limit a dispatch agent to only use listconsignments while blocking access to invoicing tools.

Deploy specialized agent teams in CrewAI to monitor CartonCloud logistics and manage warehouse MCP 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 CartonCloud MCP to CrewAI

Create your Vinkius account to connect CartonCloud 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 CartonCloud with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Autonomous Logistics Teams

Single agents struggle with complex supply chains. CrewAI lets you build a team where an Inventory Agent checks `get_product_stock` while a separate Dispatch Agent monitors `list_consignments`. They share memory and pass context back and forth to keep your transport operations running smoothly. Role-based specialization prevents hallucinations. You assign the `list_purchase_orders` tool exclusively to an Inbound Freight agent. That specific worker focuses entirely on receiving schedules and never gets confused by outbound shipping tasks.

Connect the CartonCloud MCP Server

Integrating these logistics endpoints requires zero boilerplate. You simply pass the Vinkius endpoint URL directly into the `mcps` array on your Agent definition. The framework automatically discovers the available warehouse tools and makes them available for sequential execution. Advanced setups can restrict access using `tool_filter` on the `MCPServerHTTP` class. If you want a billing agent to only see financial data, you filter its access to just `list_logistics_invoices` and `list_logistics_customers`. This keeps your specialized workers focused on their exact domain.

Monitor Sale Orders Hierarchically

Running agents in a hierarchical structure gives you a managerial layer for warehouse tasks. A manager agent can instruct a subordinate to run `list_sale_orders` and parse the outbound queue. The manager then decides which orders need immediate attention based on transport deadlines. Fetching exact details via `get_sale_order_details` gives the manager agent the precise weights and dimensions needed for transport planning. The crew handles the entire dispatch monitoring process without manual intervention, escalating issues only when physical capacity limits are reached.

Setup guide

Set up CartonCloud 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 CartonCloud tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install the framework with MCP tool support. Add your Vinkius endpoint URL to the `mcps` list when defining your agent. The worker will automatically inherit all the exposed logistics functions.

You can use the `MCPServerHTTP` class and apply a `tool_filter`. This allows you to limit a dispatch agent to only use `list_consignments` while blocking access to invoicing tools.

The framework maintains shared memory across the crew. If one agent pulls a list of outbound shipments using `list_sale_orders`, the other agents can reference that exact data during their own execution steps.

You decide the execution strategy. You can run them sequentially so the inventory check finishes before dispatch planning begins, or use a hierarchical setup where a manager agent delegates tasks dynamically.

Your data passes through a completely isolated V8 Isolate Sandbox. When your crew queries exact item quantities via `get_product_stock` or pulls specific shipment routing from `get_sale_order_details`, the compute environment is destroyed the millisecond the payload returns. Nothing persists.

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