How to Use the Flexport MCP in CrewAI

Q: How secure are my purchase orders when processed by CrewAI?

All purchase order details retrieved via getpurchaseorder are processed within Vinkius's secure MCP Server sandbox. The data is transmitted over TLS directly to your execution environment, ensuring that sensitive pricing and vendor agreements are never cached or exposed.

Run autonomous teams of specialized CrewAI agents to coordinate Flexport shipments and audit customs documents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flexport MCP to CrewAI

Create your Vinkius account to connect Flexport 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 Flexport with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent coordination for freight auditing

One agent cannot handle complex international logistics alone. CrewAI allows you to deploy a specialized team where one agent acts as a customs auditor and another as a logistics coordinator. The auditor agent runs `list_commercial_invoices` to pull billing files, while the coordinator agent uses `get_shipment` to verify physical delivery dates. They share memory to ensure your company never pays for cargo that is still stuck at sea.

Autonomous purchase order creation and tracking

Let your agent teams manage inventory replenishment autonomously. A procurement agent can use `create_purchase_order` to draft new orders based on stock levels, then hand the task to a tracking agent. The tracking agent monitors the progress by calling `get_purchase_order` and matching it with shipment milestones. If a delay is detected, the agent escalates the issue to your logistics team with a full status report.

Automate customs clearance with this MCP Server

Avoid costly port storage fees by automating document collection. This Flexport MCP Server lets a dedicated documentation agent monitor incoming shipments and gather required paperwork before the vessel docks. The agent runs `list_documents` to check for missing files, then uses `download_document` to pull the necessary bills of lading. The files are compiled and passed to your customs broker without any manual back-and-forth.

Setup guide

Set up Flexport 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 Flexport tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

CrewAI agents use a shared memory system. When a tracking agent runs `get_shipment`, the retrieved delivery dates and container numbers are immediately accessible to the billing agent running `list_shipment_invoices`.

Yes, you can use CrewAI's tool filter to restrict access. For example, you can give your tracking agent access only to `list_shipments`, while reserving `create_purchase_order` for your procurement agent.

Pass the Vinkius SSE or HTTP endpoint directly into your CrewAI Agent initialization using the `mcps` parameter. The framework automatically discovers the 12 logistics tools and makes them available to your agents.

While agents cannot move ships, they can mitigate delays. When `get_shipment` reports a delay, a CrewAI agent can automatically notify customers, update your ERP system, and draft alternative routing options.

All purchase order details retrieved via `get_purchase_order` are processed within Vinkius's secure MCP Server sandbox. The data is transmitted over TLS directly to your execution environment, ensuring that sensitive pricing and vendor agreements are never cached or exposed.

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