How to Use the Argo Workflows MCP in VS Code Copilot

Q: How do we share Argo Workflows configurations in VS Code Copilot?

Create a .vscode/mcp.json file in your repository root and commit it to Git. This allows everyone on your team using VS Code Copilot to automatically access the same MCP Server tools.

Q: Can VS Code Copilot inspect active Argo Workflows?

Yes, Copilot uses the getworkflow tool to fetch live execution trees and pod statuses. You can ask the chat assistant to explain why a specific step in your pipeline is currently stuck.

Q: How does VS Code Copilot access archived Argo Workflows?

The assistant calls listarchivedworkflows to pull historical run data into your chat workspace. This lets you compare current run errors against successful historical builds.

Team-wide Kubernetes pipeline management inside VS Code Copilot using shared configurations for active workflows.

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 VS Code Copilot

Create your Vinkius account to connect Argo Workflows to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Standardize Pipelines with this MCP Server

This configuration uses `list_workflow_templates` and `get_server_info` to ensure your entire team builds pipelines against the same cluster specifications. By committing the config to Git, every developer gets instant access to your cluster's template definitions. VS Code Copilot reads these shared templates to validate new workflow files before they are committed. This prevents broken manifests from reaching your CI/CD pipeline and wasting cluster resources.

Monitor Namespaces in VS Code Copilot

This MCP Server exposes `list_workflows` and `get_workflow` to let your team monitor active pipeline runs directly from the Copilot chat panel. Developers can check the status of their runs without needing administrative access to the Argo dashboard. Copilot parses the live resource trees to explain why a specific step is blocked. This makes it easy for developers to self-serve debugging steps instead of pinging the platform engineering team for logs.

Audit Cron Schedules and Historical Runs

This setup uses `list_cron_workflows` and `list_archived_workflows` to let your team audit scheduled jobs and historical runs directly from their workspace. The server retrieves active schedules and historical execution metadata to identify failing cron jobs. Copilot cross-references these historical runs with your active schedules to flag recurring bottlenecks. This helps your team plan resource allocation based on actual execution patterns.

Setup guide

Set up Argo Workflows MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Argo Workflows MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Argo Workflows tools listed. Try asking: "List my recent Argo Workflows transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "argo-workflows-mcp": {
      "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 VS Code Copilot

Create a `.vscode/mcp.json` file in your repository root and commit it to Git. This allows everyone on your team using VS Code Copilot to automatically access the same MCP Server tools.

Yes, Copilot uses the `get_workflow` tool to fetch live execution trees and pod statuses. You can ask the chat assistant to explain why a specific step in your pipeline is currently stuck.

The assistant calls `list_archived_workflows` to pull historical run data into your chat workspace. This lets you compare current run errors against successful historical builds.

No, the MCP Server uses your local kubeconfig permissions. VS Code Copilot can only view and list resources that your active Kubernetes user profile is authorized to access.

Your cluster metadata, workflow templates, and execution histories are handled through a secure local transport layer. The tool configurations run locally on your machine, preventing sensitive pipeline specs from being leaked to public endpoints.

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