How to Use the Virtuagym MCP in AutoGen

Q: Can AutoGen handle Virtuagym scheduling disputes?

Yes. You can have one agent checking listevents and another checking club capacity via getclubinfo. They argue over whether the schedule is viable for that week.

Q: Does the MCP Server improve decision making with AutoGen?

By providing a structured set of tools like searchmembers, it gives the debating agents concrete, verifiable data points. This means decisions are based on facts, not assumptions.

Build Consensus-Driven Decisions with AutoGen and the Virtuagym 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 Virtuagym MCP to AutoGen

Create your Vinkius account to connect Virtuagym 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 Virtuagym with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Debate using Virtuagym

Imagine a system where one agent pulls member data via `get_member`, while another cross-references that profile against current `list_events`. They don't just report; they debate the best course of action for the user. AutoGen facilitates consensus-driven decision making. If agents disagree on whether a workout plan is appropriate, they negotiate until one agent reaches a final recommendation based on all the available data from the MCP Server.

Simulating Operational Conflict

You can set up competing agents: one that prioritizes revenue by suggesting premium plans (`list_memberships`), and another focused on member satisfaction using `get_club_info`. They argue over the best recommendation. The outcome isn't a simple tool execution; it's a negotiated decision. This is perfect for complex scenarios where the answer requires deliberation between competing business perspectives.

Systematic Program Generation via MCP Server

An agent can check `list_workout_plans` and then pass those plans to another agent, which uses `list_nutrition_plans` to ensure dietary alignment. They challenge each other's assumptions until the final program is validated. This setup allows you to build systems where multiple roles—like a billing expert arguing with a wellness coach—all contribute to a single, vetted conclusion.

Setup guide

Set up Virtuagym 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 Virtuagym 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="Virtuagym_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

It uses the MCP Server's tools as inputs for multiple specialized agents. The agents discuss the data—say, a member’s profile from `get_member`—and debate the best recommendation until they reach consensus.

Yes. You can have one agent checking `list_events` and another checking club capacity via `get_club_info`. They argue over whether the schedule is viable for that week.

It handles everything: member profiles, membership plans, activity listings, and workout programs. The agents debate how to combine these different datasets into one recommendation.

By providing a structured set of tools like `search_members`, it gives the debating agents concrete, verifiable data points. This means decisions are based on facts, not assumptions.

It provides real-time access to club operational data, including current membership status and available staff lists via `list_trainers`.

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