How to Use the 99Minutos Express MCP in AutoGen

Q: What does the setup look like for 99Minutos Express tools in an AutoGen project?

You install the AutoGen MCP extension and use the mcpservertools function with your Vinkius URL. This returns a list of tools that you pass directly to your AssistantAgent constructors. The adapter handles the rest.

Let AutoGen agents debate and execute complex 99Minutos Express logistics tasks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 99Minutos Express MCP to AutoGen

Create your Vinkius account to connect 99Minutos Express 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 99Minutos Express with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Shipping Decisions

This isn't about one agent making a call. It's about a team reaching a consensus. You can have a 'Logistics' agent propose a new shipment with `create_order`. But before it executes, a 'Finance' agent automatically intercepts, calls `get_rates` to check the cost, and gives a thumbs-up or thumbs-down. This conversational approach lets you build checks and balances directly into your workflow. The shipment only gets booked after the agents agree, mirroring how a real operations team works. This MCP server gives them the tools to act on their decisions.

Collaborative Coverage Planning

Planning your expansion becomes a group task. One agent can be responsible for monitoring coverage gaps by periodically running `list_coverage`. When it finds an underserved area, it can propose a new warehouse to the group. Another agent, maybe a 'Strategy' agent, can then evaluate the proposal. Once the group of agents agrees, one of them is authorized to execute `create_store` and register the new dispatch node. It turns strategic planning into an automated, multi-perspective conversation.

Debate-Driven Order Management with AutoGen

Handle exceptions with a team of specialists. A 'Tracker' agent might use `get_tracking` and flag a stalled delivery. It could suggest using `cancel_order` immediately. But a 'Support' agent might join the conversation, arguing that canceling will upset the customer and suggest an alternative. They debate the trade-offs. The final action is a product of that negotiation, not a knee-jerk reaction from a single agent.

Setup guide

Set up 99Minutos Express 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 99Minutos Express 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="99Minutos Express_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent 99Minutos Express 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="99Minutos Express_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent 99Minutos Express 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 99Minutos App. 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 99Minutos Express 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 99Minutos Express MCP in AutoGen

You assign different roles and tools. A 'Planner' agent gets `create_order` and a 'Finance' agent gets `get_rates`. The Planner proposes, the Financier approves, and only then is the order placed. They collaborate in a group chat.

Yes, that's a perfect use case. Give that agent access to the `get_rates` tool. Set up the agent interaction so it must approve the cost before another agent is allowed to call `create_order`.

You install the AutoGen MCP extension and use the `mcp_server_tools` function with your Vinkius URL. This returns a list of tools that you pass directly to your `AssistantAgent` constructors. The adapter handles the rest.

Definitely. You can create an 'Infrastructure' agent whose job is to manage notifications. Give it the `create_webhook` and `list_webhooks` tools to configure how and where your system gets delivery updates.

The data, such as order contents and tracking coordinates, is passed as messages between your agents during their conversations. Vinkius executes the tool calls in a secure, sandboxed environment. You are in control of the agent conversation logs, which will contain that data.

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