ArgoCD MCP
An MCP (Model Context Protocol) server that integrates with the ArgoCD API, enabling AI assistants and large language models to manage ArgoCD applications and resources through natural language interactions.
What is ArgoCD MCP?
ArgoCD MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp (model context protocol) server that integrates with the argocd api, enabling ai assistants and large language models to manage argocd applications and resources through natural language interacti...
An MCP (Model Context Protocol) server that integrates with the ArgoCD API, enabling AI assistants and large language models to manage ArgoCD applications and resources through natural language interactions.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP (Model Context Protocol) server that integrates with
Use Cases
Maintainer
Works with
Installation
NPM
npx -y argocd-mcpManual Installation
npx -y argocd-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use ArgoCD MCP
argocd-mcp is an MCP server that connects AI assistants directly to the Argo CD GitOps continuous delivery platform, allowing natural language management of applications and Kubernetes resources. It supports listing, creating, updating, deleting, and syncing ArgoCD applications, as well as inspecting resource trees, managed resources, workload logs, and events — all through the standard MCP tool protocol. DevOps engineers and platform teams use it to interact with ArgoCD deployments without leaving their AI coding environment.
Prerequisites
- Node.js v18 or higher installed
- A running Argo CD instance with API access enabled
- An ArgoCD API token generated from the Argo CD UI or CLI
- The ArgoCD instance URL (e.g. https://argo.example.com)
- An MCP client such as Claude Desktop or VS Code
Obtain an ArgoCD API token
Generate an API token from your Argo CD instance. In the Argo CD UI go to Settings > Accounts, or use the argocd CLI: 'argocd account generate-token'. Note the token and your ArgoCD base URL.
argocd account generate-token --account <your-account>Test the server with npx
Run the server once directly to verify your credentials work before adding it to your MCP client config.
ARGOCD_BASE_URL=https://argo.example.com ARGOCD_API_TOKEN=your-token npx -y argocd-mcp stdioConfigure your MCP client
Add the argocd-mcp server to your MCP client configuration, passing the base URL and API token as environment variables.
Enable read-only mode for safer access (optional)
Set MCP_READ_ONLY=true to disable all write operations (create, update, delete, sync) and allow only read access to ArgoCD resources. Useful for auditing or shared environments.
Configure multiple ArgoCD instances (optional)
For multi-cluster setups, create a token registry JSON file mapping each ArgoCD base URL to its token, then pass the file path via ARGOCD_TOKEN_REGISTRY_PATH.
# token-registry.json
[
{ "baseUrl": "https://argo-a.example.com", "token": "<token-a>" },
{ "baseUrl": "https://argo-b.example.com", "token": "<token-b>" }
]ArgoCD MCP Examples
Client configuration
Add this block to your claude_desktop_config.json. Replace the placeholder values with your actual ArgoCD URL and API token.
{
"mcpServers": {
"argocd-mcp": {
"command": "npx",
"args": ["-y", "argocd-mcp@latest", "stdio"],
"env": {
"ARGOCD_BASE_URL": "https://argo.example.com",
"ARGOCD_API_TOKEN": "your-argocd-api-token"
}
}
}
}Prompts to try
Use these prompts once argocd-mcp is connected to your AI assistant.
- "List all ArgoCD applications and show their current sync status."
- "Sync the frontend-app application in ArgoCD."
- "Show me the resource tree for the payments-service application."
- "What events have occurred on the api-gateway application in the last hour?"
- "Create a new ArgoCD application called test-app pointing to the staging namespace."Troubleshooting ArgoCD MCP
TLS certificate errors when connecting to a self-signed ArgoCD instance
Set the environment variable NODE_TLS_REJECT_UNAUTHORIZED=0 in your MCP client config env block. Only use this for development or internal environments, never in production.
401 Unauthorized errors when calling ArgoCD tools
Regenerate your API token from the Argo CD UI or CLI and update ARGOCD_API_TOKEN. Tokens can expire depending on your ArgoCD configuration. Also verify ARGOCD_BASE_URL does not have a trailing slash.
Write tools like create_application or sync_application are missing
Check that MCP_READ_ONLY is not set to 'true' in your environment. When read-only mode is enabled, modification tools are intentionally excluded from the server.
Frequently Asked Questions about ArgoCD MCP
What is ArgoCD MCP?
ArgoCD MCP is a Model Context Protocol (MCP) server that mcp (model context protocol) server that integrates with the argocd api, enabling ai assistants and large language models to manage argocd applications and resources through natural language interactions. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install ArgoCD MCP?
Install via npm with the command: npx -y argocd-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with ArgoCD MCP?
ArgoCD MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is ArgoCD MCP free to use?
Yes, ArgoCD MCP is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
ArgoCD MCP Alternatives — Similar Cloud Services Servers
Looking for alternatives to ArgoCD MCP? 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 ArgoCD MCP 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 ArgoCD MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.