How to Use the AirOps MCP in Google ADK

Q: How do I connect AirOps to my agent built with Google ADK?

Use the McpToolset from the google-adk library, passing your Vinkius server URL to its StreamableHttpServerParameters. Then, include that toolset in the tools list when you initialize your LlmAgent.

Q: Can I limit which AirOps tools my Google ADK agent can use?

Yes. The McpToolset constructor accepts a toolnames filter. This lets you expose only a specific subset of the AirOps tools to your agent, which is a good practice for security and for keeping the agent focused.

Q: Does my Gemini agent get results back immediately from AirOps?

It depends. Using executeworkflowsync will block and return a result directly. If you use executeworkflowasync, it returns an ID right away, and your agent must then poll getexecutionstatus to see when the job is finished.

Connect Google ADK to AirOps to orchestrate tasks and manage agent memory, right from your Google Cloud environment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AirOps MCP to Google ADK

Create your Vinkius account to connect AirOps 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 AirOps with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger AirOps Workflows in Google Cloud

This server gives your Gemini agent direct control over AirOps workflows. Your agent can run quick, blocking jobs with `execute_workflow_sync` or fire off background processes using `execute_workflow_async`. It has the tools to pick the right execution style for the task at hand. Your agent needs to track these jobs. It uses `get_execution_status` to check on progress and `cancel_execution` to stop a task that's gone rogue. This provides the control you need to build enterprise-grade automations on top of Google Cloud.

A Searchable Memory for Google ADK

Your Gemini agent can build and maintain its own knowledge base. It uses `upload_file` to ingest new documents and `add_memory_document` to process and save that information into a searchable store. It's how you give your agent a long-term memory. Before answering a query, the agent can call `search_memory_store` to pull up relevant facts. This is how you ground your agent's large context window with specific, timely information from your own data sources, making its responses more accurate and useful.

Discover and Interact with AirOps Apps

This MCP Server allows your agent to discover its own capabilities. It can call `list_apps` to see every AirOps application it can access. From there, `get_app_details` fetches the specific metadata for any single app. This lets your agent build a coherent plan before it acts. It can even use `chat_with_agent` to communicate with other specialized agents inside the AirOps environment. This is a critical component for building multi-agent systems on Google Cloud.

Setup guide

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

Use the `McpToolset` from the `google-adk` library, passing your Vinkius server URL to its `StreamableHttpServerParameters`. Then, include that toolset in the `tools` list when you initialize your `LlmAgent`.

Yes. The `McpToolset` constructor accepts a `tool_names` filter. This lets you expose only a specific subset of the AirOps tools to your agent, which is a good practice for security and for keeping the agent focused.

AirOps provides a ready-made set of tools for common agent operations like async execution and memory search. You don't have to build, deploy, or maintain that infrastructure yourself. This MCP Server just works out of the box.

It depends. Using `execute_workflow_sync` will block and return a result directly. If you use `execute_workflow_async`, it returns an ID right away, and your agent must then poll `get_execution_status` to see when the job is finished.

The server handles instructions for your workflows and any data you send with tools like `upload_file` or `add_memory_document`. Vinkius processes this data in a completely isolated, zero-trust environment that is destroyed after your request. We do not keep your workflow 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