How to Use the Sellfy MCP in AutoGen

Q: How do I load Sellfy tools into AutoGen?

Install autogen-extmcp. Use mcpservertools with a StreamableHttpServerParams configuration pointing to your endpoint. Pass the returned list into your AssistantAgent constructor.

Q: Why use AutoGen for Sellfy instead of a single script?

Scripts follow rigid logic. AutoGen handles ambiguity. If getproductdetails returns a missing description, one agent can draft a new one while another reviews it for brand voice before updating the catalog.

Q: Does AutoGen support the Sellfy MCP Server over standard IO?

Yes. The McpToolAdapter handles the schema conversion automatically. You can connect via standard IO or Streamable HTTP transports depending on your deployment architecture.

Build AutoGen agent swarms to debate and manage your Sellfy store.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sellfy MCP to AutoGen

Create your Vinkius account to connect Sellfy to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sellfy with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Swarm-Based Sellfy Order Processing

The `list_orders` and `get_order_details` tools feed raw transaction data directly into your AutoGen swarm. A primary agent fetches the recent sales, while secondary agents analyze the line items for fraud or fulfillment priority. They don't just process the data blindly. An inventory agent might flag a high-volume purchase, prompting a security agent to debate whether the order looks legitimate. They negotiate a conclusion before approving the fulfillment step.

Autonomous Store Management

Using `get_store_information` and `list_store_coupons`, your agents monitor the high-level health of your storefront. They can check active discounts and debate if a new promotion is necessary based on recent sales velocity. If they decide you need a new digital download, they can draft the details and execute `create_product`. You define the boundaries, but the multi-agent system handles the actual decision-making and API execution.

Customer Churn Debate via MCP Server

The MCP Server provides `list_subscriptions` and `get_subscription_details` to your conversational framework. A retention agent pulls expiring recurring profiles and proposes win-back offers. A finance agent reviews the proposed discounts against `list_customers` data to ensure profitability. They argue over the margin impact. Once they reach consensus, they output a finalized list of users to email.

Setup guide

Set up Sellfy 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 Sellfy 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="Sellfy_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Sellfy 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="Sellfy_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Sellfy 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 Sellfy. 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 Sellfy 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 Sellfy MCP in AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with a `StreamableHttpServerParams` configuration pointing to your endpoint. Pass the returned list into your `AssistantAgent` constructor.

Yes. You assign the tool list to specific agents in your swarm. A dedicated data-gathering agent might hold `list_products`, while an execution agent holds `create_product`.

Scripts follow rigid logic. AutoGen handles ambiguity. If `get_product_details` returns a missing description, one agent can draft a new one while another reviews it for brand voice before updating the catalog.

Yes. The `McpToolAdapter` handles the schema conversion automatically. You can connect via standard IO or Streamable HTTP transports depending on your deployment architecture.

Your agents pull raw PII like subscriber names, billing intervals, and customer emails from `get_subscription_details`. This data sits in the active context window during the multi-agent debate. The MCP Server strictly isolates the fetch request, but you must ensure your LLM provider doesn't train on your conversation logs.

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