How to Use the Airship MCP in Google ADK

Q: Can Google ADK restrict which Airship tools the agent sees?

You can pass a toolnames filter when building the toolset. This lets you expose listsegments for reading data while blocking sendpushnotification to prevent accidental messages.

Q: How does the Airship MCP Server handle large audience lists?

Tools like listnamedusers return paginated or structured data. Gemini absorbs these lists into its massive token context window to reason about the entire audience at once.

Connect Airship to Google ADK and let Gemini drive mobile messaging.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Airship MCP to Google ADK

Create your Vinkius account to connect Airship 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 Airship with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Drive Airship campaigns with Gemini

The Airship MCP Server links your Google Cloud data directly to mobile engagement tools. Your LlmAgent calls `send_push_notification` to fire alerts based on anomalies detected in BigQuery or Vertex AI pipelines. Gemini's massive context window means it can evaluate thousands of rows of telemetry before acting. It runs `get_push_status` to verify delivery and feeds that success rate back into your analytics tables.

Target specific user hardware

Resolving identity across enterprise datasets requires precise mapping. The agent executes `list_channels` to find active app installations and `get_channel_details` to read the device metadata. Once the hardware is identified, the system calls `associate_named_user` to bind that phone or tablet to a central customer ID. This ensures your BigQuery records match the actual notification targets.

Parse complex audience rules via MCP Server

Enterprise marketing relies on deep segmentation. Your Google ADK setup queries `list_segments` and `list_static_lists` to pull all available audience cohorts into the model's memory. Because Gemini holds so much context, it can read the output of `get_segment_details` and `list_tags` simultaneously. The agent cross-references these rules against your internal data to pick the exact right audience for a push.

Setup guide

Set up Airship 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 Airship 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="Airship_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Airship 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 Airship. 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 Airship 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 Airship MCP in Google ADK

Install google-adk and set up McpToolset with StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset into your LlmAgent initialization.

You can pass a tool_names filter when building the toolset. This lets you expose list_segments for reading data while blocking send_push_notification to prevent accidental messages.

Tools like list_named_users return paginated or structured data. Gemini absorbs these lists into its massive token context window to reason about the entire audience at once.

The framework supports both Stdio and HTTP transports natively. Vinkius provides the managed HTTP endpoint, so you just drop the URL into your server parameters.

Vinkius isolates the MCP Server connection using a zero-trust sandbox. The notification text, segment criteria, and device IDs travel securely between Google Cloud and the API without hitting persistent storage.

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