How to Use the airfocus MCP in Google ADK

Q: How do I connect my Google ADK agent to this airfocus server?

You'll use the McpToolset from the Google ADK library. Just initialize it with the Vinkius URL for this MCP server and pass the toolset to your LlmAgent during setup. The tools are then available to the agent.

Q: Is it possible to limit a Google ADK agent to only read data from airfocus?

Yes, easily. When you configure the McpToolset, use the toolnames filter to specify only the read-only tools like listairfocusitems and getairfocusitem. This prevents the agent from being able to call createairfocusitem or updateairfocusitem.

Connect your Gemini agents to airfocus. Let your Google ADK agents reason over your entire product roadmap and act on it.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect airfocus MCP to Google ADK

Create your Vinkius account to connect airfocus 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 airfocus with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage airfocus Items with Gemini Agents

Let your Gemini agents directly manage your product backlog in airfocus. An agent running on Google Cloud can `create_airfocus_item` for a new feature or `update_airfocus_item` with the latest status. This connects your AI logic directly to your product planning tools. This is where Google ADK's power becomes clear. An agent can analyze data in BigQuery, use Gemini's massive context window to compare it against your entire airfocus backlog from `list_airfocus_items`, and then propose a strategically sound new feature. It's not just automation; it's data-driven action.

Bridge Your Roadmap to Google Cloud Data

Your agents need context. They can get it by pulling data straight from airfocus. Use `list_airfocus_workspaces` to see all your product areas or `get_airfocus_item` to get the specifics on a single initiative. The agent gets a live view of your roadmap. With Google ADK, your agent can take that airfocus data and cross-reference it with information in your Google Cloud ecosystem. It can compare roadmap priorities against customer support tickets in BigQuery or model outputs from Vertex AI. This gives your agent a much deeper, enterprise-level understanding before it acts.

An MCP Server Built for Google ADK

Integration is clean. You set up the `McpToolset` with the Vinkius server URL and pass it to your `LlmAgent`. Your agent is immediately equipped to talk to airfocus. No complex configuration needed. Google ADK's `tool_names` filter gives you precise control. You can build focused agents for specific jobs. For example, create a read-only reporting agent by exposing only `list_airfocus_items` and `get_airfocus_item`. Then create a separate 'editor' agent with access to `update_airfocus_item`. It's the kind of granular control needed for enterprise systems.

Setup guide

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

You'll use the `McpToolset` from the Google ADK library. Just initialize it with the Vinkius URL for this MCP server and pass the toolset to your `LlmAgent` during setup. The tools are then available to the agent.

Yes. Your Google ADK agent can fetch a large number of items using `list_airfocus_items` and load that data into the Gemini model's context window. This allows the agent to reason over your entire backlog at once.

Yes, easily. When you configure the `McpToolset`, use the `tool_names` filter to specify only the read-only tools like `list_airfocus_items` and `get_airfocus_item`. This prevents the agent from being able to call `create_airfocus_item` or `update_airfocus_item`.

This server uses a Vinkius endpoint token for authentication, which is separate from your GCP identity. You manage access by issuing and revoking these tokens, giving you a distinct control layer for external tools.

It accesses your airfocus roadmap items, workspaces, and field definitions. Security is handled by Vinkius's zero-trust architecture. Your connection uses a single, revocable token, and every request runs in a new, ephemeral instance that's destroyed after completion.

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