Unraid
A Python-based server that enables AI assistants to interact with an Unraid server through the official Unraid GraphQL API, providing read-only access to system information, Docker containers, VMs, storage, and more.
What is Unraid?
Unraid is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to python-based server that enables ai assistants to interact with an unraid server through the official unraid graphql api, providing read-only access to system information, docker containers, vms, stor...
A Python-based server that enables AI assistants to interact with an Unraid server through the official Unraid GraphQL API, providing read-only access to system information, Docker containers, VMs, storage, and more.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Python-based server that enables AI assistants to interact
Use Cases
Maintainer
Works with
Installation
PIP
pip install unraid-mcpManual Installation
pip install unraid-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Unraid
The Unraid MCP Server is a Python-based FastMCP server that connects AI assistants to an Unraid NAS/homelab system via the official Unraid GraphQL API, providing comprehensive read and management access to system information, Docker containers, virtual machines, array health, storage shares, plugins, and real-time live data streams. It exposes a unified tool interface with over 18 action groups covering everything from parity checks and rclone operations to WebSocket-based live CPU and memory monitoring, making it the most complete AI interface for Unraid homelab management.
Prerequisites
- Unraid 6.12 or later with the Unraid API enabled
- An Unraid API key from Settings → Management Access → API Keys in the Unraid web UI
- Python 3.11+ and uv installed on the machine running the MCP server
- Network access from the MCP server host to your Unraid GraphQL endpoint
- An MCP-compatible client: Claude Desktop, Claude Code, or Cursor
Install the package via pip
Install unraid-mcp from PyPI. Using uv is recommended for isolated environment management.
pip install unraid-mcp
# or with uv:
uv add unraid-mcpCreate a .env configuration file
Copy the example env file and fill in your Unraid server's GraphQL URL and API key. The API key is generated in the Unraid web UI under Settings → Management Access → API Keys.
UNRAID_API_URL=https://tower.local/graphql
UNRAID_API_KEY=your_unraid_api_key_here
UNRAID_MCP_PORT=6970
UNRAID_MCP_TRANSPORT=streamable-httpStart the MCP server
Launch the server. It will listen on port 6970 by default and serve requests via HTTP transport.
uv run unraid-mcp-serverConfigure your MCP client
Add the Unraid MCP server to your Claude Desktop config. Since it runs as an HTTP server, use the URL-based transport configuration.
{
"mcpServers": {
"unraid": {
"command": "uvx",
"args": ["unraid-mcp"],
"env": {
"UNRAID_API_URL": "https://tower.local/graphql",
"UNRAID_API_KEY": "your_unraid_api_key_here"
}
}
}
}Test the connection
Ask Claude to get a system overview. Destructive operations require an explicit confirm=True parameter as a safety mechanism.
Unraid Examples
Client configuration
claude_desktop_config.json entry for Unraid MCP using uvx to run the installed package.
{
"mcpServers": {
"unraid": {
"command": "uvx",
"args": ["unraid-mcp"],
"env": {
"UNRAID_API_URL": "https://tower.local/graphql",
"UNRAID_API_KEY": "your_unraid_api_key_here",
"UNRAID_MCP_PORT": "6970"
}
}
}
}Prompts to try
Explore your Unraid server using natural language with these example prompts.
- "Give me a full overview of my Unraid server's health and array status."
- "List all running Docker containers and show which ones are stopped."
- "Start a parity check on my array and monitor the progress."
- "Show me real-time CPU and memory usage on my Unraid server."
- "List all VMs and their current power states."Troubleshooting Unraid
Connection refused or GraphQL endpoint unreachable
Verify UNRAID_API_URL is correct and accessible from your machine (ping tower.local or use the IP address). Ensure the Unraid API is enabled in Settings → Management Access and that no firewall blocks the connection.
API key authentication errors
Regenerate the API key in Unraid's web UI under Settings → Management Access → API Keys and update UNRAID_API_KEY in your .env file. Restart the MCP server after updating.
SSL certificate errors with HTTPS Unraid URL
If Unraid uses a self-signed certificate, the server may reject it. Check the repository for an UNRAID_IGNORE_SSL or similar option, or configure your Unraid instance with a valid certificate via Let's Encrypt.
Frequently Asked Questions about Unraid
What is Unraid?
Unraid is a Model Context Protocol (MCP) server that python-based server that enables ai assistants to interact with an unraid server through the official unraid graphql api, providing read-only access to system information, docker containers, vms, storage, and more. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Unraid?
Install via pip with: pip install unraid-mcp. Then configure your AI client to connect to this MCP server.
Which AI clients work with Unraid?
Unraid works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Unraid free to use?
Yes, Unraid is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Unraid Alternatives — Similar Cloud Services Servers
Looking for alternatives to Unraid? 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 Unraid 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 Unraid?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.