How to Use the GoBolt MCP in OpenAI Agents SDK

Q: How do I configure the GoBolt MCP Server within my OpenAI Agents SDK pipeline?

Install the library using pip install openai-agents. Instantiate the connection with MCPServerStreamableHttp using your GoBolt endpoint, then pass the server object directly into your Agent's mcpservers list.

Q: Can the OpenAI Agents SDK automatically select shipping carriers using GoBolt?

Yes. Your agent calls findcheapestrate to compare carrier pricing, then uses createshippingorder to book the package. You can set strict budget guardrails in the SDK to prevent the agent from selecting rates above a specific threshold.

Q: How does caching work when using GoBolt with the OpenAI Agents SDK?

Set cacheToolsList=True in your SDK configuration. This prevents the agent from querying the server for tool definitions on every single request, keeping your shipping rate checks fast.

Q: What happens if a shipment needs to be modified mid-transit?

Your agent calls modifyshippingorder to update the delivery address or package weight. The SDK routes this action through your validation layer to confirm the package hasn't already shipped.

Run high-volume logistics agents with the OpenAI Agents SDK and GoBolt to safely route orders and compare shipping rates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GoBolt MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated shipping rate optimization

The GoBolt MCP Server exposes real-time carrier pricing directly to your OpenAI Agents SDK runtimes, letting your agent run `get_shipping_rates` instantly. You don't have to write custom API integrations to find the best carrier for every package. When a customer places an order, your agent executes `find_cheapest_rate` or `find_fastest_rate` based on the delivery SLA. The built-in OpenAI guardrails validate these costs before committing to a carrier, preventing expensive errors.

Safe shipping order fulfillment via MCP Server

This MCP Server lets your OpenAI Agents SDK system build complete fulfillment pipelines without manual intervention. The agent uses `create_shipping_order` to book shipments and immediately calls `get_shipping_labels` to grab the printable PDFs. If a customer updates their address, your specialized support agent handles the change via `modify_shipping_order`. The agent-to-agent handoff in OpenAI's SDK ensures only authorized support agents alter active shipments.

Real-time tracking and exception handling

Your OpenAI Agents SDK monitors active shipments by calling `track_shipment` to pull current transit statuses. If a package is stalled, the agent digs into the timeline with `get_tracking_history` to diagnose the delay. You can view every step of this tracking loop in your OpenAI dashboard. The agent pulls `get_order_details` to verify the customer's contact info, then messages them with an updated delivery estimate.

Setup guide

Set up GoBolt 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 GoBolt tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the library using `pip install openai-agents`. Instantiate the connection with `MCPServerStreamableHttp` using your GoBolt endpoint, then pass the server object directly into your Agent's `mcp_servers` list.

Yes. Your agent calls `find_cheapest_rate` to compare carrier pricing, then uses `create_shipping_order` to book the package. You can set strict budget guardrails in the SDK to prevent the agent from selecting rates above a specific threshold.

Set `cacheToolsList=True` in your SDK configuration. This prevents the agent from querying the server for tool definitions on every single request, keeping your shipping rate checks fast.

Your agent calls `modify_shipping_order` to update the delivery address or package weight. The SDK routes this action through your validation layer to confirm the package hasn't already shipped.

The Vinkius MCP Server manages your credentials inside a secure V8 sandbox. Your OpenAI Agents SDK only interacts with the sandboxed tools, meaning raw merchant API keys and customer shipping labels are never exposed to the LLM context.

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