How to Use the ONES MCP in Google ADK

Q: How do I initialize the ONES MCP Server inside Google ADK?

Use the McpToolset class with your Vinkius HTTP server parameters. Pass this toolset directly to your LlmAgent instance to make all ten project management tools available to Gemini.

Q: Can Google ADK agents run complex ONES workflow updates?

Yes, the agent can fetch the allowed transitions using listworkflows and then execute the state change with updatetask. Gemini's reasoning handles the multi-step logic easily.

Control your ONES project boards with Google ADK using Gemini's massive context window to analyze entire developer backlogs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ONES MCP to Google ADK

Create your Vinkius account to connect ONES to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ONES with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Analyze entire backlogs using Google ADK and Gemini

Gemini's million-token context window lets your Google ADK agent swallow your entire issue history in one go by calling `list_tasks` and `get_task_details`. The agent builds a complete picture of your R&D velocity. It can spot bottlenecks that standard dashboard metrics miss. You can feed these raw task descriptions and sprint histories into your Google ADK agent to generate release notes or clean up stale tickets. The agent uses `update_task` to close out old work without you having to click through a web interface.

Map enterprise R&D structures to BigQuery data

Combine your live project tracking with your enterprise data warehouse by linking BigQuery metrics against active ONES tickets fetched via `list_projects` and `get_org_info`. Once the agent identifies who is working on what, it uses `list_members` to verify assignments. You automate resource planning directly within your Google Cloud infrastructure without manual data exports.

Configure the ONES MCP Server with Gemini tools

Setting up this MCP server inside your Google Cloud environment takes only a few lines of Python to initialize `list_workflows` and `list_task_types`. If you want to restrict what the agent can do, use the optional tool filter to limit access. You can let the agent inspect things with `get_project` while blocking write operations if you want a read-only assistant.

Setup guide

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

Use the `McpToolset` class with your Vinkius HTTP server parameters. Pass this toolset directly to your `LlmAgent` instance to make all ten project management tools available to Gemini.

Yes, the agent can fetch the allowed transitions using `list_workflows` and then execute the state change with `update_task`. Gemini's reasoning handles the multi-step logic easily.

You should implement standard backoff strategies in your agent loop. When calling `list_tasks` repeatedly, the ADK manages the tool execution pipeline to avoid hitting platform API limits.

Yes, the toolset constructor accepts a filter argument where you can specify allowed tool names. This lets you expose only safe tools like `get_project` while hiding modification tools.

Your sensitive ticket descriptions, workflow states, and team member lists are processed in an isolated, zero-trust sandbox. Communication between Google Cloud and the API is encrypted, and no data is persisted on Vinkius.

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