How to Use the AirLabs MCP in Google ADK

Q: How do I configure the AirLabs MCP with Google ADK?

Install the google-adk package. Initialize a McpToolset using StreamableHttpServerParameters and your endpoint URL. Pass this toolset to your LlmAgent configuration.

Q: Can I restrict which AirLabs tools my Google ADK agent uses?

You can filter the exposed functions using the optional toolnames parameter in the ADK setup. This prevents the agent from calling getschedules if you only want it monitoring real-time data with getflights.

Q: How does AirLabs handle airline searches in Google ADK?

The getairlines tool lets your agent search by country, IATA code, or callsign. It returns founding years, fleet sizes, and hub information. Gemini uses this metadata to add context to flight tracking queries.

Q: What happens if the user only knows part of an airport name?

The agent calls autocompleteairport to resolve the input. It returns a ranked list of matches with full ICAO codes. This prevents the agent from guessing and failing subsequent API calls.

Feed live global aviation data directly into your Gemini models using the AirLabs MCP server and Google ADK.

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 Google ADK

Create your Vinkius account to connect AirLabs to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Aviation Data for Gemini Workloads

`get_flights` feeds real-time aircraft positions, speeds, and altitudes straight into your Google ADK environment. You filter by airline or geographic bounding box to monitor active airspace. `get_flight_info` pulls the granular terminal and gate data for specific flight numbers. Gemini models excel at processing massive datasets. You can dump hundreds of active flights into the 1M+ token context window. The agent analyzes traffic patterns and cross-references them with your existing BigQuery datasets in real time.

Analyze Airline Fleets via MCP Server

`get_airline_fleet` dumps the entire aircraft inventory of any airline, detailing engine types, delivery dates, and current operational status. `get_airline_routes` maps out every route pair and service frequency. You get complete visibility into an airline's operational footprint. Enterprise agents on Google Cloud use this for market analysis. Your Gemini agent pulls the fleet data and immediately structures it for Vertex AI pipelines. It turns raw aviation metrics into actionable competitor intelligence without manual data engineering.

Ground Operations and Delay Prediction

`get_airport_delays` returns precise delay metrics, historical comparisons, and cancellation rates. `get_flights_by_airport` provides the full context of what is landing or taking off. `get_nearby_airports` identifies alternate landing zones based on coordinates. You combine these tools to build predictive logistics agents. When an agent detects high delay indicators at a major hub, it automatically evaluates the surrounding regional airports. The ADK handles the HTTP transport layer silently while your agent does the heavy lifting.

Setup guide

Set up AirLabs MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with AirLabs tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="AirLabs_agent",
    model="gemini-2.0-flash",
    instruction="You have access to AirLabs tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the `google-adk` package. Initialize a `McpToolset` using `StreamableHttpServerParameters` and your endpoint URL. Pass this toolset to your `LlmAgent` configuration.

You can filter the exposed functions using the optional `tool_names` parameter in the ADK setup. This prevents the agent from calling `get_schedules` if you only want it monitoring real-time data with `get_flights`.

The `get_airlines` tool lets your agent search by country, IATA code, or callsign. It returns founding years, fleet sizes, and hub information. Gemini uses this metadata to add context to flight tracking queries.

The agent calls `autocomplete_airport` to resolve the input. It returns a ranked list of matches with full ICAO codes. This prevents the agent from guessing and failing subsequent API calls.

The integration only queries public aviation metrics like transponder hex codes, route pairs, and delay statistics. No proprietary corporate data or user identities pass through the tools. Vinkius enforces zero-trust authentication, meaning your endpoint token is the only access key.

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