How to Use the AirLabs MCP in AutoGen

Q: How do I register AirLabs MCP Server tools with AutoGen?

Use the mcpservertools helper from the autogen-ext package. This registers tools like getflights directly to your AutoGen assistant agents.

Q: Can I use partial airport names in AutoGen?

Yes, your coordinator agent can use autocompleteairport to resolve a user's typed string before passing the clean IATA code to other agents.

Let your AutoGen agents debate flight schedules and coordinate complex logistics with real-time aviation data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AirLabs MCP to AutoGen

Create your Vinkius account to connect AirLabs 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 AirLabs with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent flight schedule coordination

`get_schedules` retrieves planned flight timetables and aircraft assignments between specific airport pairs. Your AutoGen travel agent uses this data to draft itineraries, while a budgeting agent reviews the options. They debate the best routes based on layover times and carrier reliability. The conversation continues until both agents agree on an optimal plan, eliminating single-agent planning errors.

Collaborative delay and routing analysis

`get_airport_delays` pulls live performance metrics and delay trends for departure and arrival airports. An operational agent monitors these metrics to flag potential missed connections in real-time. If delays spike, the agent passes the problem to a routing agent equipped with `get_nearby_airports`. They negotiate alternative entry points, finding nearby runways to keep your cargo or passengers moving.

AutoGen MCP Server aircraft verification

`get_aircraft` details specific airframe registration, model, and operational status using a unique transponder hex code. This MCP Server tool lets your verification agent check the exact specifications of incoming aircraft. A separate safety agent can cross-reference these specs against current airport operational limits. This multi-agent debate ensures that only compliant aircraft are cleared for simulated flight plans.

Setup guide

Set up AirLabs 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 AirLabs 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="AirLabs_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the `mcp_server_tools` helper from the `autogen-ext` package. This registers tools like `get_flights` directly to your AutoGen assistant agents.

Yes, different agents in your group chat can call different tools like `get_airlines` or `get_airport_delays` as needed during their debate.

The agents negotiate. For example, one agent checks scheduled times with `get_schedules` while another checks active status with `get_flight_info` to resolve discrepancies.

Yes, your coordinator agent can use `autocomplete_airport` to resolve a user's typed string before passing the clean IATA code to other agents.

Vinkius routes all fleet and route requests through isolated HTTP tunnels. Your authentication keys never touch the AutoGen agent runtime or any external logging 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