How to Use the Goody MCP in OpenAI Agents SDK

Q: How do I handle batch gifting errors in OpenAI Agents SDK?

Your agent monitors the batch status using getorderbatch to catch any delivery or address failures. The SDK's tracing dashboard logs these tool outputs, making it easy to debug failed recipient lines.

Q: Does this MCP Server support real-time inventory checks?

Yes, the server exposes listinventory to pull live stock levels directly into your agent's context. This prevents your OpenAI Agents SDK pipeline from attempting to send gifts that are out of stock.

Get your OpenAI Agents SDK pipelines sending corporate gifts and checking inventory automatically with the Goody MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Goody MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Browse the Goody MCP Server catalog from OpenAI Agents SDK

The `list_products` tool lets your agent pull active gift inventories directly into your OpenAI Agents SDK pipeline. You don't have to hardcode product IDs or manually verify what's currently in stock before running a gifting run. Your agent uses `get_product` to grab specific details like pricing or shipping restrictions before proposing a gift to your sales team. This keeps the agent's product selection accurate and prevents it from picking items that are backordered or unavailable.

Batch gift orders with strict guardrails

The `create_order_batch` tool processes bulk corporate gifts directly inside your OpenAI Agents SDK workflows. Instead of writing custom API wrappers, your agent passes recipient lists straight to this tool to trigger shipments. You can route these orders through the SDK's built-in validation layer to prevent accidental double-gifting. The agent checks `list_order_batches` to confirm past runs before committing a new batch, keeping your billing predictable.

Track campaign performance in real-time

The `list_campaigns` tool retrieves active marketing and outreach campaigns so your agent can map gifts to specific corporate objectives. You get direct access to campaign metadata without leaving your Python environment. After launching, the agent queries `get_campaign` and `list_recipients` to monitor who accepted their gifts and who needs a follow-up. This gives your sales team an automated feedback loop directly inside their custom dashboard.

Setup guide

Set up Goody 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 Goody tools at runtime.
3

Create your Agent

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

Run the agent

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

You register the server using MCPServerStreamableHttp and pass it to your Agent constructor. The MCP Server auto-discovers all 11 tools, allowing your agent to call `list_products` or `create_order_batch` natively.

Yes, you configure this at the agent definition level in Python. By limiting the tool list passed to the constructor, you ensure the agent only uses `list_orders` or `get_order` without exposing batch creation tools.

Your agent monitors the batch status using `get_order_batch` to catch any delivery or address failures. The SDK's tracing dashboard logs these tool outputs, making it easy to debug failed recipient lines.

Yes, the server exposes `list_inventory` to pull live stock levels directly into your agent's context. This prevents your OpenAI Agents SDK pipeline from attempting to send gifts that are out of stock.

All recipient addresses and order histories are handled inside Vinkius's secure sandboxed MCP environment. Your API keys are never exposed to the LLM, and data transmission relies on encrypted, ephemeral isolates that destroy session logs immediately after the agent runs.

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