How to Use the Arrivy MCP in OpenAI Agents SDK

Q: How do I initialize the Arrivy MCP Server in my OpenAI Agents SDK pipeline?

Install the SDK and pass the Vinkius HTTP URL to MCPServerStreamableHttpParams. Then, add the server instance directly to your Agent constructor's mcpservers list.

Q: What is the best way to cache the Arrivy tool definitions in OpenAI Agents SDK?

Set cacheToolsList=True in your connection parameters. This stops the SDK from querying the Vinkius server for the tool schema on every single message turn, dropping latency.

Coordinate last-mile deliveries and manage field crews with Arrivy using the OpenAI Agents SDK and managed MCP endpoints.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arrivy MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dispatch field crews from OpenAI Agents

`list_crews` fetches active field personnel data so your OpenAI Agents SDK can make scheduling decisions. The agent inspects available crews and instantly assigns jobs without manual dispatching. This setup runs inside your OpenAI tracing dashboard, meaning you see every single MCP tool call to `list_crews` and `update_task` with zero guesswork. You can track latency and check payloads directly from your browser.

Safe customer onboarding and validation

`create_customer` writes new client profiles directly into Arrivy from your OpenAI agent. Before execution, the OpenAI Agents SDK applies your custom guardrails to verify the customer payload. If the agent attempts to create a duplicate customer or missing address, the SDK intercepts the execution before hitting this MCP Server. This keeps your field database clean.

Update Arrivy Tasks using OpenAI Agents SDK

`update_task` modifies existing field orders when your OpenAI agent receives updates from the field. You can pass off task modifications to a specialized dispatch agent that handles only scheduling conflicts. It uses the Vinkius managed endpoint to connect your Python runtime directly to the Arrivy MCP Server, keeping your agent logic lean. Your production deployment stays lightweight and fast.

Setup guide

Set up Arrivy 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 Arrivy tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Arrivy 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="Arrivy Agent",
            instructions="You have access to Arrivy 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 Arrivy. 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 Arrivy 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 Arrivy MCP in OpenAI Agents SDK

Install the SDK and pass the Vinkius HTTP URL to `MCPServerStreamableHttpParams`. Then, add the server instance directly to your `Agent` constructor's `mcp_servers` list.

Yes. The SDK automatically resolves these tools from the Arrivy endpoint and executes them concurrently if your model decides to fetch both task lists and crew availability at once.

You define guardrails directly on your OpenAI agent. The agent checks the proposed parameters against your schema before sending the payload to the Arrivy tool.

Set `cacheToolsList=True` in your connection parameters. This stops the SDK from querying the Vinkius server for the tool schema on every single message turn, dropping latency.

Your customer addresses and field task descriptions pass through Vinkius inside an ephemeral, zero-trust V8 sandbox. No data is stored on Vinkius servers, and the connection uses a single token to talk directly to the Arrivy API.

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