Can my AI agent figure out exactly which pod/node failed in an active workflow execution?

Yes. If a workflow fails, you can ask your agent to retrieve the workflow tree by name. The agent uses the `get_workflow` tool to inspect the deeply nested structure, traverse the active nodes, and pinpoint the exact step or container that resulted in an error state without you ever needing to click through the Argo UI.

Can I list only scheduled periodic jobs across my cluster?

Absolutely. You can use the dedicated `list_cron_workflows` capability to isolate and return strictly workloads orchestrated on a time schedule across any namespace, saving you from parsing through thousands of isolated runs.

Do I need to expose my internal Kubernetes API to use this?

No. The integration strictly interfaces with the Argo Server UI/API layer via standard REST traffic using a scoped ServiceAccount Bearer token. Your cluster's overarching master `kube-apiserver` remains safely isolated from external agentic logic.

Argo Workflows MCP Server for Google ADK 6 tools — connect in under 2 minutes

Name: Argo Workflows
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 6 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Argo Workflows as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="argo_workflows_agent",
    instruction=(
        "You help users interact with Argo Workflows "
        "using 6 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Argo Workflows MCP Server

Connect your Argo Workflows cluster to any AI agent and take full control of your infrastructure orchestration through natural conversation.

Google ADK natively supports Argo Workflows as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 6 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Active Workflows — List and query all running, pending, or recently completed workflow executions across your Kubernetes namespaces
Deep Inspection — Dive into specific workflow instances to inspect their precise resource trees, node statuses, and pod parameters to catch failures
Templates & Crons — Browse parameterized, reusable WorkflowTemplates and analyze recurring CronWorkflows orchestrating scheduled jobs
Historical Archives — Search archived workflows that hit your database to understand historical infrastructure patterns

The Argo Workflows MCP Server exposes 6 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Argo Workflows to Google ADK via MCP

Follow these steps to integrate the Argo Workflows MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 6 tools from Argo Workflows via MCP

Why Use Google ADK with the Argo Workflows MCP Server

Google ADK provides unique advantages when paired with Argo Workflows through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Argo Workflows

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Argo Workflows tools with BigQuery, Vertex AI, and Cloud Functions

Argo Workflows + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Argo Workflows MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Argo Workflows and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Argo Workflows tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Argo Workflows regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Argo Workflows

Argo Workflows MCP Tools for Google ADK (6)

These 6 tools become available when you connect Argo Workflows to Google ADK via MCP:

get_server_info

Get Argo Workflows server information

get_workflow

Get detailed resource tree and status for an Argo workflow

list_archived_workflows

List archived workflows from Argo history

list_cron_workflows

List scheduled cron workflows in a namespace

list_workflow_templates

List workflow templates defined in a namespace

list_workflows

List workflows in a Kubernetes namespace

Example Prompts for Argo Workflows in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Argo Workflows immediately.

"List all active workflows in the 'data-engineering' namespace."

"What is the detailed status tree of the workflow named 'daily-backup-55x'?"

"Are there any parameterized WorkflowTemplates available for me to run?"

Troubleshooting Argo Workflows MCP Server with Google ADK

Common issues when connecting Argo Workflows to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Argo Workflows + Google ADK FAQ

Common questions about integrating Argo Workflows MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.