How to Use the Argo Workflows MCP in Claude Code

Q: How do I pipe Argo Workflows data from Claude Code to other CLI tools?

You can ask Claude Code to list runs using listworkflows and format the output as raw JSON. From there, pipe it directly into standard terminal utilities like jq or awk.

Q: How do I add this server to my CLI configuration?

Use the command line utility to run claude mcp add. Pass the transport type and your Vinkius endpoint URL before specifying the server name.

Control your Kubernetes pipelines directly from your terminal using Claude Code and live cluster data.

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 Claude Code

Create your Vinkius account to connect Argo Workflows to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe pipeline statuses into terminal utilities

The agent calls `list_workflows` to fetch running processes and outputs clean text that you can pipe directly into grep or jq. Run Claude Code in your terminal to inspect active jobs without kubectl. This makes it simple to write quick shell scripts that monitor your cluster. You get immediate answers without wading through massive JSON payloads.

Troubleshoot cron jobs from the CLI

Claude Code uses `list_cron_workflows` to check your active timers and pinpoint which schedules are lagging. Avoid opening heavy browser dashboards when schedules act up. It cross-references these issues with your archived runs using `list_archived_workflows`. You get a fast, terminal-based post-mortem of your cron health in seconds.

Inspect cluster setups via this MCP Server

The agent calls `get_server_info` to check your current version and active namespace configurations directly from the command line. Get instant context about your orchestration environment. This MCP Server connects directly to your cluster, combining version data with `get_workflow` to verify that your cluster has the right resources for upcoming runs.

Setup guide

Set up Argo Workflows MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see argo-workflows-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Argo Workflows transactions." It will automatically discover and invoke the available Argo Workflows tools.

Terminal

claude mcp add --transport http argo-workflows-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Argo Workflows MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "argo-workflows-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

You can ask Claude Code to list runs using `list_workflows` and format the output as raw JSON. From there, pipe it directly into standard terminal utilities like jq or awk.

Yes. Since Claude Code runs entirely in the terminal, it can use `get_workflow` to pull pod errors during an SSH session or inside a container.

Yes. You can script Claude Code to fetch active configurations using `list_workflow_templates` and compare them against your repository files during CI/CD checks.

Use the command line utility to run `claude mcp add`. Pass the transport type and your Vinkius endpoint URL before specifying the server name.

The MCP Server runs inside a secure, ephemeral sandbox on Vinkius. Your API keys and raw logs are processed through secure HTTP transports and never stored or shared.

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