How to Use the Moova MCP in OpenAI Agents SDK

Q: How do I install the Moova MCP server in my OpenAI Agents SDK project?

Run pip install openai-agents to get started. Then, instantiate the server using MCPServerStreamableHttp with your Vinkius endpoint URL and pass it to the Agent constructor.

Q: Does the OpenAI Agents SDK cache the Moova tool definitions?

Yes, you should set cacheToolsList=True in your configuration. This prevents your agent from requesting the 14 logistics tools from the MCP Server on every single turn, keeping latency low.

Q: How does the agent handle carrier selection when creating a shipment?

When the agent invokes createshipment, the platform automatically assigns the best carrier and route based on real-time availability. You do not need to write custom routing logic or manually assign carriers.

Let your OpenAI Agents SDK dispatch shipments, fetch real-time carrier rates, and print labels with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moova MCP to OpenAI Agents SDK

Create your Vinkius account to connect Moova to OpenAI Agents SDK 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 Moova with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe shipping operations via OpenAI Agents SDK

Your production agent can spin up shipping orders safely because OpenAI's framework intercepts actions before they hit the real world. By exposing `create_shipment` via our MCP Server, your dispatch agent maps customer orders to physical logistics without risking invalid addresses or accidental carrier bookings. The system handles the heavy lifting of carrier assignment automatically based on real-time availability. You get complete traceability on the OpenAI dashboard for every single execution. If an agent needs to fix a typo, it can run `update_shipment` before pickup occurs, or invoke `cancel_shipment` if a customer cancels their order. These safety boundaries prevent costly physical mistakes while keeping your logistics pipeline automated.

Automated rate quoting and carrier selection

Instead of hardcoding shipping rules, let your agent dynamically assess costs for every order. The agent calls `get_budget` to pull live pricing across express, same-day, and standard shipping options. This lets your system choose the best carrier without human intervention. Once the optimal route is selected, the agent pulls the physical shipping document using `get_shipment_label`. This fetches the barcode and routing data required by the carrier, passing it directly to your warehouse printing queue.

Real-time tracking and event-driven updates

Keep your database in sync without polling APIs constantly. By connecting this MCP Server, your agent can register endpoints via `create_webhook` to listen for immediate delivery updates. If you ever need to clean up obsolete endpoints, the agent runs `delete_webhook` to keep your environment tidy. For on-demand customer inquiries, the agent checks the live status using `get_shipment_status` or retrieves the full history with `track_shipment`. This keeps your support desk informed without manual tracking lookups.

Setup guide

Set up Moova MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Moova tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Moova tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Moova tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Moova Agent",
            instructions="You have access to Moova tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Moova. 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 Moova 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 Moova MCP in OpenAI Agents SDK

Run `pip install openai-agents` to get started. Then, instantiate the server using `MCPServerStreamableHttp` with your Vinkius endpoint URL and pass it to the `Agent` constructor.

Yes, you can set up a specialized logistics agent that only has access to `create_shipment` and `get_shipment_label`. Your routing agent can hand off the conversation to this specialist whenever a user asks to ship an order.

Yes, you should set `cacheToolsList=True` in your configuration. This prevents your agent from requesting the 14 logistics tools from the MCP Server on every single turn, keeping latency low.

When the agent invokes `create_shipment`, the platform automatically assigns the best carrier and route based on real-time availability. You do not need to write custom routing logic or manually assign carriers.

All shipping addresses, contact details, and package dimensions sent to the tools are processed in an ephemeral V8 sandbox. Vinkius handles the authorization tokens securely, meaning your raw credentials never touch the client-side agent logs.

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