How to Use the Wing Assistant MCP in AutoGen

Q: Does the MCP Server support multi-agent conversations with AutoGen?

It does. Agents can call tools like listtasks and then use the returned data to argue about the next best course of action, leading to a consensus decision.

Achieve consensus on tasks with Wing Assistant and AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wing Assistant MCP to AutoGen

Create your Vinkius account to connect Wing Assistant 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 Wing Assistant with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Simulating Debate with the MCP Server

You can build multi-agent systems where agents argue over a decision. For instance, one agent might use `get_assistant` to check credentials while another uses `list_tasks` to verify workload capacity. The debate converges on a final conclusion based on input from multiple tools calls orchestrated by the MCP Server.

Deliberating Task Creation with AutoGen

Instead of one agent just running `create_task`, you can have agents challenge each other's proposed titles or descriptions. One might flag a resource conflict, and another might suggest a better description. This consensus-driven approach ensures the final task assignment is vetted by multiple perspectives before it hits the system.

Monitoring Workflow Status in Multi-Agent Systems

When an agent needs to know if work is proceeding, it can call `get_task_status`. Multiple agents can then debate *why* the status is stuck—one might check `list_assistants` for resource constraints while another suggests calling `update_task`. It turns a simple status check into a full diagnostic conversation.

Setup guide

Set up Wing Assistant 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 Wing Assistant 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="Wing Assistant_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The MCP Server tools are incorporated into the agent's knowledge base, allowing agents to use task data and assistant details as part of their deliberation process.

Yes. You set up a conversation where multiple specialized agents debate the parameters (title/description) before one agent executes `create_task`, ensuring high confidence in the outcome.

This server provides structured data about virtual assistants, task records (status, title, description), and lists of all available units of work. The agents debate these facts.

It does. Agents can call tools like `list_tasks` and then use the returned data to argue about the next best course of action, leading to a consensus decision.

It prevents single points of failure. You force multiple agents to check task status or create tasks, making sure that any critical assignment has been reviewed and agreed upon by consensus.

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