How to Use the Goody MCP in AutoGen

Q: How do I register Goody tools with AutoGen?

Use the mcpservertools helper from autogen-ext to connect to your Vinkius URL. This automatically converts the MCP server schema into tools that your AssistantAgent can understand.

Q: Can AutoGen agents run Goody campaigns autonomously?

Yes, your agents can use listcampaigns and createorderbatch to run gifting workflows. We recommend adding a human-in-the-loop approval step before executing final orders.

Q: How do AutoGen agents resolve Goody gift selection conflicts?

One agent queries listproducts while another checks the budget rules. They pass messages back and forth until they find a product that satisfies both constraints.

Let AutoGen agents debate budget and inventory constraints to pick and send the perfect corporate gifts autonomously.

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 AutoGen

Create your Vinkius account to connect Goody to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate gift selections with AutoGen agents

The `list_products` tool feeds raw catalog data directly into your multi-agent conversation. A budget agent can argue with a sales agent over which corporate gifts fit a specific client tier, using real pricing. Once they agree, `get_product` pulls the final specs to verify stock. The AutoGen framework ensures no single agent makes a bad purchasing decision without consensus.

Coordinate multi-agent order execution

The `create_order_batch` tool is called only after your security agent and finance agent sign off on the transaction. This consensus-driven process prevents unauthorized bulk orders from being sent to the Goody API. After the order goes through, another agent can monitor `get_order_batch` to track delivery. If a shipment gets delayed, the tracking agent alerts the customer service agent to handle outreach.

Audit campaign performance via agent debate

The `list_campaigns` tool lets your analytic agents review active marketing setups. One agent can pull campaign metrics while another compares them against physical inventory levels using `list_inventory`. This collaborative audit helps your team identify which gift campaigns are driving the most value. Because the MCP server provides live data, your agents make decisions based on real-world numbers.

Setup guide

Set up Goody MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Goody tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Goody_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Goody data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Goody_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Goody data")
    print(result.messages[-1].content)

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 AutoGen

Use the mcp_server_tools helper from autogen-ext to connect to your Vinkius URL. This automatically converts the MCP server schema into tools that your AssistantAgent can understand.

Yes, your agents can use `list_campaigns` and `create_order_batch` to run gifting workflows. We recommend adding a human-in-the-loop approval step before executing final orders.

One agent queries `list_products` while another checks the budget rules. They pass messages back and forth until they find a product that satisfies both constraints.

It supports both stdio and Streamable HTTP transports. When hosted on Vinkius, you will use the Streamable HTTP params to connect your local agents to the remote server.

Yes, your API keys and corporate order batch details are isolated in a secure, stateless execution container. Vinkius prevents any data persistence, meaning your transactional metadata is wiped clean the second your agents finish their conversation.

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