Nixopus
Run production apps without thinking about infrastructure. On your server or ours. Fully agentic.
What is Nixopus?
Nixopus is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to run production apps without thinking about infrastructure. on your server or ours. fully agentic.
Run production apps without thinking about infrastructure. On your server or ours. Fully agentic.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Run production apps without thinking about infrastructure. O
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx nixopusConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Nixopus
Nixopus is an open-source, self-hostable deployment platform with an integrated AI agent that manages the entire application lifecycle — from analyzing your codebase and generating Docker configs to deploying, monitoring, and automatically fixing failures. It supports any containerizable stack (Next.js, Django, Rails, Go, FastAPI, Docker Compose) and provides automatic TLS via Caddy, custom domain management, instant rollbacks, and multi-server orchestration from a single dashboard. Developers and small teams use it as a self-hosted alternative to Heroku or Coolify, with the added capability of a conversational AI agent they can talk to from the dashboard or directly from their editor via a VS Code / Cursor extension.
Prerequisites
- A Linux server with root access (VPS, bare metal, or cloud instance) with ports 80 and 443 open
- An API key from a supported LLM provider: OpenRouter, OpenAI, Anthropic, Google, DeepSeek, or Groq
- Docker and Docker Compose installed on the target server (the install script handles this)
- A domain name pointed at your server's IP (optional but required for automatic HTTPS)
- An MCP-compatible client such as Claude Code or Cursor for editor-based deployments
Run the one-line installer on your server
SSH into your server and run the installer script. Pass environment variables for your domain, admin email, and LLM provider API key. The installer sets up Docker, Caddy, the Nixopus API, and configures TLS automatically.
# Minimal install (IP-only access)
curl -fsSL install.nixopus.com | sudo bash
# With custom domain and Anthropic Claude as the AI backend
curl -fsSL install.nixopus.com | sudo DOMAIN=panel.example.com [email protected] LLM_PROVIDER=anthropic ANTHROPIC_API_KEY=sk-ant-xxxxx bash
# With OpenRouter (default LLM provider)
curl -fsSL install.nixopus.com | sudo DOMAIN=panel.example.com OPENROUTER_API_KEY=sk-or-xxxxx bashAccess the Nixopus dashboard
Once the installer completes, open your browser to your configured domain (or server IP on port 80). Log in with the admin email you specified during installation.
Connect your GitHub account
In the dashboard, navigate to Integrations and link your GitHub account. This allows Nixopus to read your repositories, detect your stack, and create pull requests with automatic fix commits when deployments fail.
Deploy your first application
Open the Chat interface and tell the AI agent to deploy a repository. The agent analyzes the codebase, detects your framework, generates the build configuration, and deploys the app — assigning it an HTTPS URL automatically.
Add the editor extension for in-IDE deployments
Install the Nixopus extension for VS Code or Cursor. Connect it to your Nixopus instance URL. You can then deploy, check logs, roll back, and troubleshoot directly from your editor sidebar without opening a browser.
Configure MCP for AI client integration
Add Nixopus as an MCP server in your Claude Desktop or Cursor MCP configuration to enable conversational deployment management from any MCP client.
Nixopus Examples
Client configuration
Add Nixopus as an MCP server. Replace the URL with your Nixopus instance address and provide your instance API token.
{
"mcpServers": {
"nixopus": {
"command": "npx",
"args": ["nixopus"],
"env": {
"NIXOPUS_API_URL": "https://panel.example.com",
"NIXOPUS_API_TOKEN": "your-api-token-here"
}
}
}
}Prompts to try
These prompts work in the Nixopus dashboard chat or through an MCP-connected AI client.
- "Deploy the main branch of my-org/my-nextjs-app to production."
- "Add the custom domain app.mysite.com to the frontend deployment."
- "Show me the last 100 log lines for the API container."
- "Roll back the backend to the previous deployment."
- "The deployment failed — diagnose the error and fix it automatically."Troubleshooting Nixopus
Caddy fails to provision a TLS certificate for the custom domain
Ensure your domain's DNS A record points to the server's public IP and that ports 80 and 443 are open in your firewall or cloud security group. Caddy uses Let's Encrypt HTTP-01 challenge, which requires port 80 to be reachable from the internet.
The AI agent fails to detect my stack or generates an incorrect build config
Tag the relevant resources in the chat using @App or @Container to give the agent focus. If the repo has an unusual structure, provide a brief description in your message: 'This is a FastAPI app with a Dockerfile in the backend/ subdirectory.'
Install script fails or Nixopus containers do not start
Check that Docker is not already running conflicting containers on ports 80 or 443. Review logs with 'docker compose -f /opt/nixopus/docker-compose.yml logs'. The default installation directory is /opt/nixopus and can be overridden with NIXOPUS_HOME.
Frequently Asked Questions about Nixopus
What is Nixopus?
Nixopus is a Model Context Protocol (MCP) server that run production apps without thinking about infrastructure. on your server or ours. fully agentic. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Nixopus?
Follow the installation instructions on the Nixopus GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Nixopus?
Nixopus works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Nixopus free to use?
Yes, Nixopus is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Nixopus Alternatives — Similar Cloud Services Servers
Looking for alternatives to Nixopus? 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 Nixopus 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 Nixopus?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.