How to Use the Evolio MCP in AutoGen

Q: How do I give Evolio tools to my AutoGen agents?

You'll need the autogen-extmcp package. Use the mcpservertools function with your Vinkius server URL to get a list of tools. Then, just pass that tool list into your AssistantAgent constructor.

Q: Can multiple AutoGen agents work on the same Evolio case?

Yes, that's the point. One agent can getcase details, another can listtasksbycase, and a third can createtask. They coordinate through conversation to manage the case collaboratively.

Create teams of AI agents in AutoGen to manage your Evolio coaching practice through conversation and debate.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Evolio MCP to AutoGen

Create your Vinkius account to connect Evolio 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 Evolio with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Case Reviews with Agent Teams

AutoGen is different. You build teams of agents that talk to each other to solve a problem. You can create a 'Reviewer' agent that uses `get_case` and `list_tasks_by_case` to analyze a client's progress. Then, a 'Strategist' agent can take that data and propose next steps. They'll debate the best course of action in a conversation. Once they agree, one of them calls `create_task` or `update_case`. The final action is based on consensus.

Build a Client Intake Team

You can automate your front office. Design an 'Intake' agent that receives a new client request. It talks to a 'Records' agent, which uses `list_clients` to check if the person is already in the system. Based on the answer, the Intake agent can decide to `create_case` for the new client. This conversational workflow replaces manual email chains and checklists. It's a system of specialists working together.

Multi-Agent Reporting with this MCP Server

Forget writing status reports. Have your agents do it. One agent's only job is to run `list_cases_by_status` every morning to find cases that are stuck or falling behind. It then passes that list to a 'Reporter' agent. The Reporter agent then uses `get_client` and `get_case` to gather details for each one, formats a summary, and sends it to you. This MCP server provides the tools; AutoGen provides the conversational workflow to use them effectively.

Setup guide

Set up Evolio 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 Evolio 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="Evolio_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You'll need the `autogen-ext[mcp]` package. Use the `mcp_server_tools` function with your Vinkius server URL to get a list of tools. Then, just pass that tool list into your `AssistantAgent` constructor.

Yes, that's the point. One agent can `get_case` details, another can `list_tasks_by_case`, and a third can `create_task`. They coordinate through conversation to manage the case collaboratively.

The agent chooses based on its instructions, the ongoing conversation, and the user's goal. If you ask it to 'check on Client X', it knows from the tool descriptions that `get_client` and `list_cases` are the right place to start.

Yes, the conversation history is a core part of AutoGen. You can review the entire debate between agents, seeing which tools they considered, what data they found with tools like `get_case`, and why they made their final decision.

Your client data—names, case notes, task details—will exist in the conversation history between your AutoGen agents. You must secure the environment where your agents run. While the connection to the Evolio MCP server is secure, the agents' memory and logs are your responsibility to protect.

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