How to Use the Ezus MCP in AutoGen

Q: How do AutoGen agents debate billing details from Ezus?

One agent calls getinvoice to pull the billing data while another runs getclient to check client contract terms. They compare the data and flag errors if the amounts don't match.

Q: Can I register the Ezus MCP Server with multiple AutoGen agents?

Yes. You use mcpservertools to load the tools and pass the list to the AssistantAgent constructors. This lets all agents in your group query the same database.

Q: How do agents handle conflicting updates to projects?

Agents use the getproject tool to check the current state before executing upsertproject. If a conflict occurs, they negotiate a resolution before writing the final update.

Q: What is the configuration steps for using the Ezus MCP Server with AutoGen?

Install autogen-extmcp and configure the client with your Vinkius HTTP URL. The adapter automatically translates the tool schemas so your agents can call them directly.

Let your AutoGen agents debate and coordinate travel bookings directly inside Ezus using this 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 Ezus MCP to AutoGen

Create your Vinkius account to connect Ezus 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 Ezus with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve booking conflicts with AutoGen agent debates

The `upsert_project` tool allows your primary booking agent to write new itineraries directly to your database. Before finalizing, a second agent runs `get_project` to check for overlapping dates or double-booked suppliers. If a conflict is found, the agents debate the best alternative. They resolve the scheduling issue autonomously and write the clean, verified itinerary back to the system.

Audit billing and invoices via multi-agent MCP consensus

The `list_invoices` tool lets your financial auditor agent retrieve outstanding billing statements. The agent coordinates with a client manager agent that runs `get_client` to confirm if payment terms match the client's contract. This multi-agent workflow catches billing errors before they reach the customer. The agents agree on the correct amounts and flag discrepancies for your accounting team.

Coordinate supplier selection autonomously

The `list_suppliers` tool exposes your entire vendor registry to your sourcing agent. When a new travel project is created, the sourcing agent queries `list_products` to find matching packages and negotiates the best options with your planning agent. The agents select the optimal supplier based on budget constraints. Once they reach a consensus, they call `upsert_project` to link the selected vendor directly to the customer's itinerary.

Setup guide

Set up Ezus 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 Ezus 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="Ezus_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One agent calls get_invoice to pull the billing data while another runs get_client to check client contract terms. They compare the data and flag errors if the amounts don't match.

Yes. You use mcp_server_tools to load the tools and pass the list to the AssistantAgent constructors. This lets all agents in your group query the same database.

Agents use the get_project tool to check the current state before executing upsert_project. If a conflict occurs, they negotiate a resolution before writing the final update.

Install autogen-ext[mcp] and configure the client with your Vinkius HTTP URL. The adapter automatically translates the tool schemas so your agents can call them directly.

Yes. Vinkius runs the server in an ephemeral sandbox. Your supplier rates, margins, and contact details retrieved via get_supplier are processed in memory and never stored.

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