How to Use the Argo Workflows MCP in CrewAI

Q: How do I add Argo Workflows to a CrewAI agent?

Use the MCPServerHTTP helper from the CrewAI library and pass the Vinkius URL. You can assign specific tools to individual agents, giving your monitor agent access to listworkflows while restricting administrative tools.

Deploy a collaborative team of CrewAI agents to monitor, audit, and debug Argo Workflows autonomously.

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 CrewAI

Create your Vinkius account to connect Argo Workflows to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent cluster operations with CrewAI

Set up a dedicated team where one agent monitors active runs and another handles debugging. The monitoring agent uses `list_workflows` to spot stuck jobs, then hands the task to a specialist. The debugging agent calls `get_workflow` to inspect the exact pod failure logs and suggest fixes. They collaborate using shared memory to solve cluster issues without human intervention.

Audit historical cluster trends using CrewAI agents

Let your agent team analyze long-term performance bottlenecks. A research agent uses `list_archived_workflows` to pull historical data, while an analyst agent flags slow-running steps. They compile their findings into a markdown report. This gives your platform team clear insights into where resources are being wasted without manual data gathering.

Automate scheduled job validation

Keep your cron jobs running smoothly by letting agents verify templates. One agent pulls current templates via `list_workflow_templates`, and another checks them against active crons using `list_cron_workflows`. If they find a mismatch, they draft a pull request to correct the configuration. The entire process runs in the background, keeping your cluster in sync.

Setup guide

Set up Argo Workflows MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Argo Workflows tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Argo Workflows Analyst",
    goal="Access and analyze Argo Workflows data via MCP.",
    backstory="Expert analyst with direct Argo Workflows access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Argo Workflows transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Argo Workflows Analyst",
        goal="Access and analyze Argo Workflows data via MCP.",
        backstory="Expert analyst with direct Argo Workflows access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Argo Workflows transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Use the `MCPServerHTTP` helper from the CrewAI library and pass the Vinkius URL. You can assign specific tools to individual agents, giving your monitor agent access to `list_workflows` while restricting administrative tools.

Yes, CrewAI supports sequential execution where the output of one agent becomes the input for the next. For example, one agent lists active workflows, and the next agent inspects a specific failed workflow.

The framework uses a shared memory system that allows agents to pass tool outputs to each other. When an agent calls `get_workflow`, the resulting resource tree is stored in the shared context for other agents to analyze.

It supports SSE, stdio, and Streamable HTTP transports out of the box. For serverless or containerized setups, the HTTP transport provides the most reliable connection to the Vinkius gateway.

The agent only accesses Kubernetes workflow metadata, execution states, and template definitions. All communication is encrypted in transit, and the Vinkius sandbox ensures your cluster credentials never leak to the LLM provider.

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