How to Use the Axonaut MCP in AutoGen

Get agents debating your ERP data in AutoGen by adding this MCP Server to your stack.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Axonaut MCP to AutoGen

Create your Vinkius account to connect Axonaut 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 Axonaut with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate your Axonaut workflow

Set up a performance agent and a security agent to discuss the output of `list_expenses`. They challenge each other's interpretation of your spending patterns until they reach a consensus. This system forces deliberation. You get a better result because the agents verify the data against each other's constraints before finalizing a decision.

Multi-agent CRM collaboration

Use `list_contacts` to feed your agent team the information they need to draft outreach strategies. One agent drafts the plan while the other critiques it based on past project performance. Your agents negotiate the best path forward. They don't just execute a single command; they talk through the implications of the data they retrieved from the ERP.

Automated ERP decision loops

Trigger `list_orders` when your analysts need to verify stock levels or shipping status. The agents review the raw JSON and debate the best way to report the findings to you. This creates a system where the AI handles the back-and-forth required for complex operational tasks. You set the goal and watch the agents iterate until they agree on the output.

Setup guide

Set up Axonaut 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 Axonaut 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="Axonaut_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You pass the server tools into the AssistantAgent constructor. The adapter handles the schema conversion, allowing your agents to call ERP functions during their debates.

Yes, by assigning multiple roles, you create a system where one agent can flag a record while another investigates it. They converge on a conclusion based on the evidence.

Your data stays in an ephemeral V8 sandbox. Each agent only receives the specific records it needs for its part of the discussion.

No, Vinkius handles the authentication for you. You just provide the endpoint token and the server handles the rest.

All task data is processed within an isolated environment that clears after every session. No trace of your internal task lists persists on our servers.

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