How to Use the Argo Workflows MCP in Google ADK

Q: How do I use Argo Workflows tools within a Google ADK agent?

You'll use the McpToolset class from the google-adk library, pointing it at your Vinkius MCP endpoint. Pass that toolset to your LlmAgent and it automatically discovers tools like listworkflows from the MCP Server.

Q: Is there a way to filter the Argo tools for my agent?

Yes. The McpToolset constructor accepts a toolnames argument. You can provide a list of specific tool names, like 'getworkflow', 'listworkflows', to restrict what the agent can see and do.

Connect Google ADK agents to your Argo Workflows for large-scale analysis and automation across 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 Argo Workflows MCP to Google ADK

Create your Vinkius account to connect Argo Workflows 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 Argo Workflows with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Correlate Argo Data in BigQuery

Your Gemini-powered agent can pull workflow data right from Argo. Use `list_archived_workflows` to fetch thousands of historical runs, then have the agent load that data into a BigQuery table for analysis. It’s a direct path from your Kubernetes cluster to your data warehouse. You can finally ask questions about long-term workflow performance without building a custom ETL pipeline. Your agent does the work.

Monitor Clusters with Long Context

Give your agent a high-level goal, like "Summarize the health of all workflows in the 'production' namespace." With Gemini's large context window, the agent can call `list_workflows`, then loop through the results calling `get_workflow` for each failed one. It holds all that information in its context to generate a single, coherent summary of your cluster's state. You don't have to stitch together multiple calls yourself.

Manage Argo from Your Google Cloud MCP Server

This isn't just a monitoring tool. Your Google ADK agent can inspect infrastructure definitions with `list_workflow_templates` and check schedules with `list_cron_workflows`. Since the agent is running within your GCP environment, it can easily cross-reference this information with other Google Cloud services. It could trigger a Pub/Sub notification or update a status in Firestore, making Argo another integrated part of your cloud.

Setup guide

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

You'll use the `McpToolset` class from the `google-adk` library, pointing it at your Vinkius MCP endpoint. Pass that toolset to your `LlmAgent` and it automatically discovers tools like `list_workflows` from the MCP Server.

Yes, as long as the Vinkius MCP Server has network access to your Argo Workflows API endpoint. The agent itself only needs to talk to Vinkius, which securely proxies the requests to your infrastructure.

It's the tight integration with Google Cloud and Gemini's large context. Your agent can pull massive amounts of workflow data with `list_archived_workflows` and reason about it in a single pass, or pipe it directly into BigQuery for later analysis.

Yes. The `McpToolset` constructor accepts a `tool_names` argument. You can provide a list of specific tool names, like `['get_workflow', 'list_workflows']`, to restrict what the agent can see and do.

The MCP Server only interacts with Argo's API to fetch workflow metadata—names, statuses, schedules, and logs. It doesn't access container data or secrets. All connections are ephemeral and proxied through Vinkius's zero-trust sandbox.

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