Argo Workflows
An MCP server for running Argo workflows, written in Golang
What is Argo Workflows?
Argo Workflows is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for running argo workflows, written in golang
An MCP server for running Argo workflows, written in Golang
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP server for running Argo workflows, written in Golang
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-argoConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Argo Workflows
The MCP Argo Server is a Go-based MCP server that wraps Argo Workflows, enabling AI assistants to submit, monitor, and retrieve results from Argo workflow executions on Kubernetes through natural language commands. It communicates over STDIO using JSON-RPC and leverages client-go for Kubernetes API access and Argo Workflows client libraries. This server bridges the gap between AI agents and Kubernetes-native workflow orchestration, making it possible to trigger data pipelines and automation workflows conversationally.
Prerequisites
- Go 1.21 or higher installed
- A running Kubernetes cluster with Argo Workflows installed (or the included k3d dev environment)
- kubectl configured with access to the target cluster
- An MCP-compatible client such as Claude Desktop or an AutoGen-based agent
Clone the repository
Clone the mcp-argo-server repository and navigate into the project directory.
git clone https://github.com/jakkaj/mcp-argo-server.git
cd mcp-argo-serverInstall Go dependencies
Run go mod tidy to download and verify all required Go module dependencies.
go mod tidySet up the local dev cluster (optional)
Use the included Makefile target to create a local k3d cluster with Argo Workflows pre-installed. Verify it is working by checking cluster info.
make cluster
kubectl cluster-info
# Verify Argo UI at https://localhost:2746/workflows/argo/Submit a test workflow to confirm Argo is working
Submit the included hello-world workflow template to verify your Argo setup before connecting the MCP server.
argo submit -n argo --watch ./kube/argo-hello-world.yamlBuild and run the MCP server
Compile and start the MCP server. It communicates over STDIN/STDOUT so it should be launched by an MCP client rather than run standalone.
make runConfigure your MCP client
Add the compiled binary path to your MCP client configuration so the client can launch the server as a subprocess.
Argo Workflows Examples
Client configuration
Claude Desktop configuration to launch the MCP Argo server binary as a subprocess with STDIO transport.
{
"mcpServers": {
"argo-workflows": {
"command": "/path/to/mcp-argo-server/mcp-argo-server",
"args": []
}
}
}Prompts to try
Example prompts for managing Argo Workflows through an AI assistant.
- "Submit the hello-world workflow to the argo namespace"
- "What is the status of my running workflows?"
- "Wait for workflow <name> to complete and show me the results"
- "List all workflows in the argo namespace with their current status"Troubleshooting Argo Workflows
kubectl or Argo commands fail with connection refused
Ensure your kubeconfig is correctly configured and the cluster is running. For the local dev setup, run `make cluster` to create the k3d cluster and wait for all pods to be Ready before starting the MCP server.
MCP server exits immediately when run directly
The server communicates over STDIO and expects to be launched by an MCP client as a subprocess. Running it standalone will exit because there is no client sending JSON-RPC messages. Use `make run` only for build verification.
Workflow submission fails with namespace errors
Argo Workflows is installed in the `argo` namespace by the `make cluster` target. Ensure workflow submissions specify `-n argo` and that the service account has the necessary RBAC permissions in that namespace.
Frequently Asked Questions about Argo Workflows
What is Argo Workflows?
Argo Workflows is a Model Context Protocol (MCP) server that mcp server for running argo workflows, written in golang It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Argo Workflows?
Follow the installation instructions on the Argo Workflows GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Argo Workflows?
Argo Workflows works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Argo Workflows free to use?
Yes, Argo Workflows is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Argo Workflows Alternatives — Similar Cloud Services Servers
Looking for alternatives to Argo Workflows? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Argo Workflows in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Argo Workflows?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.