Argo Workflows

Argo Workflows MCP Connector for Claude

D

Automate Kubernetes orchestrations via Argo Workflows — monitor, list, and inspect active pods, crons, and workflow templates directly from any AI agent.

6 tools Official Updated Jun 28, 2026 Official Vinkius Partner

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

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

How it works

  1. Subscribe to this server
  2. Enter your Argo Cluster Server URL and RBAC Bearer Token
  3. Start querying your execution trees from Claude, Cursor, or any MCP-compatible client

No more wrestling with kubectl CLI tools or constantly refreshing the Argo Web UI to find out why a step failed. Your AI acts as your ultimate DevOps copilot.

Who is this for?

  • DevOps & Platform Teams — debug pipeline failures, check node statuses, and audit running jobs without leaving your terminal or chat workflow
  • Data Engineers — monitor complex ETL workflows and scheduled cron operations seamlessly
  • SREs — quickly query the health of the Argo server and retrieve historical archiving metrics
kubernetesworkflow-automationcontainer-orchestrationci-cdinfrastructure-as-codejob-scheduling

6 tools expose this connector's capabilities to your AI agent.

list_workflows

List workflows in a Kubernetes namespace

get_workflow

Get detailed resource tree and status for an Argo workflow

list_workflow_templates

List workflow templates defined in a namespace

list_cron_workflows

List scheduled cron workflows in a namespace

list_archived_workflows

List archived workflows from Argo history

get_server_info

Get Argo Workflows server information

See how to talk to your AI agent using Argo Workflows.

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

I found 4 active workflows in 'data-engineering'. Three are executing robustly, but 'etl-nightly-pipeline' has been pending for 22 minutes. Would you like me to get the deep tree view of this pipeline to see which pod is stuck?

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

I've inspected the tree for 'daily-backup-55x'. The master process reports 'Failed'. Specifically, node 's3-upload-step' crashed exiting with code 1. The previous node 'pg-dump' succeeded. It seems to be an S3 permission issue in the pod parameter payload.

Are there any parameterized WorkflowTemplates available for me to run?

Listing your templates... You have 3 reusable components: `model-training-tmpl` (requires hyperparameters as array input), `data-cleanup` (expects an S3 bucket URI), and `slack-notification-hook`. They are all initialized and stored in the default namespace.

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.

Related Connectors