How to Use the JSONCargo Maritime MCP in OpenAI Agents SDK

Q: How do I connect JSONCargo Maritime to my OpenAI Agents SDK pipeline?

Install the package and initialize MCPServerStreamableHttp pointing to the Vinkius JSONCargo Maritime endpoint. Pass this server instance in the mcpservers list when instantiating your OpenAI Agents SDK Agent.

Q: Does the OpenAI Agents SDK support caching for JSONCargo Maritime tools?

Yes, you set cacheToolsList=True in the server parameters of your OpenAI Agents SDK configuration. This prevents the SDK from pulling JSONCargo Maritime schemas like listmaritimeports on every single turn, reducing latency.

Run production-grade OpenAI Agents SDK workflows with real-time JSONCargo Maritime vessel tracking and automated voyage auditing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JSONCargo Maritime MCP to OpenAI Agents SDK

Create your Vinkius account to connect JSONCargo Maritime 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 JSONCargo Maritime with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-discover JSONCargo Maritime tools in OpenAI Agents SDK

`search_maritime_vessels` lets your OpenAI Agents SDK instance find ships by their IMO or name without manual tool mapping. The OpenAI Agents SDK automatically inspects the JSONCargo Maritime endpoint, registers the schemas, and exposes the vessel search tool to your specialized agents. Setting `cacheToolsList=True` in your OpenAI Agents SDK Python code avoids extra network roundtrips when your agents query active JSONCargo Maritime shipping routes. This caching mechanism ensures your vessel search operations execute with minimal latency.

Validate voyage audits with built-in guardrails

`get_current_voyage_details` retrieves active transit logs that your OpenAI Agents SDK agent validates before triggering downstream logistics tasks. The OpenAI Agents SDK compares the current voyage telemetry against planned routes to flag deviations immediately. You can set up handoffs between an OpenAI Agents SDK tracking agent and a billing agent to process JSONCargo Maritime data. If the voyage data shows a vessel reached its destination, the tracking agent hands off the task to the billing agent with zero manual intervention.

Check API status before executing agent handoffs

`check_api_status` verifies the endpoint is active before your OpenAI Agents SDK system triggers complex maritime lookups using the MCP Server. Running this check first prevents your OpenAI Agents SDK pipelines from stalling on dead connections. The OpenAI Agents SDK handles streamable HTTP connections to the JSONCargo Maritime server safely. If the status check fails, your OpenAI Agents SDK agent pauses execution or routes the task to a fallback queue instead of failing silently.

Setup guide

Set up JSONCargo Maritime 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 JSONCargo Maritime tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package and initialize `MCPServerStreamableHttp` pointing to the Vinkius JSONCargo Maritime endpoint. Pass this server instance in the `mcp_servers` list when instantiating your OpenAI Agents SDK Agent.

Yes, you set `cacheToolsList=True` in the server parameters of your OpenAI Agents SDK configuration. This prevents the SDK from pulling JSONCargo Maritime schemas like `list_maritime_ports` on every single turn, reducing latency.

Yes, you can design one OpenAI Agents SDK agent to search vessels with `search_maritime_vessels` and hand the data to a port specialist agent. The port agent then calls `list_maritime_ports` to find open berths.

The OpenAI Agents SDK catches the HTTP error from the JSONCargo Maritime server and passes the raw failure message back to the agent. The agent can then use `check_api_status` to determine if it should retry or alert your team.

All vessel logs, IMO numbers, and voyage details pass through the secure Vinkius V8 sandbox hosting the MCP Server. Your OpenAI Agents SDK credentials never touch the underlying JSONCargo Maritime database directly, keeping your shipping manifests safe.

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