1Panel
An MCP server for 1Panel, a modern Linux server operation and maintenance panel.
1Panel MCP Server
1Panel MCP Server is an implementation of the Model Context Protocol (MCP) server for 1Panel.
Installation Methods
Method 1: Download from Release Page (Recommended)
-
Visit the Releases Page and download the executable file corresponding to your system.
-
Example installation (for amd64):
chmod +x mcp-1panel-linux-amd64
mv mcp-1panel-linux-amd64 /usr/local/bin/mcp-1panel
Method 2: Build from Source
Make sure Go 1.23 or later is installed locally. Then run:
- Clone the repository:
git clone https://github.com/1Panel-dev/mcp-1panel.git
cd mcp-1panel
- Build the executable:
make build
Move ./build/mcp-1panel to a directory included in your system's PATH.
Method 3: Install via go install
Make sure Go 1.23 or later is installed locally. Then run:
go install github.com/1Panel-dev/mcp-1panel@latest
Method 4: Install via Docker
Make sure Docker is correctly installed and configured on your machine.
The official image supports the following architectures:
- amd64
- arm64
- arm/v7
- s390x
- ppc64le
Usage
1Panel MCP Server supports two running modes: stdio and sse.
stdio Mode
Using Local Binary
In the configuration file of Cursor or Windsurf, add:
{
"mcpServers": {
"mcp-1panel": {
"command": "mcp-1panel",
"env": {
"PANEL_ACCESS_TOKEN": "<your 1Panel access token>",
"PANEL_HOST": "such as http://localhost:8080"
}
}
}
}
Running in Docker
{
"mcpServers": {
"mcp-1panel": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PANEL_HOST",
"-e",
"PANEL_ACCESS_TOKEN",
"1panel/1panel-mcp-server"
],
"env": {
"PANEL_HOST": "such as http://localhost:8080",
"PANEL_ACCESS_TOKEN": "<your 1Panel access token>"
}
}
}
}
sse Mode
- Start the MCP Server:
mcp-1panel -host http://localhost:8080 -token <your 1Panel access token> -transport sse -addr http://localhost:8000
- Configure in Cursor or Windsurf:
{
"mcpServers": {
"mcp-1panel": {
"url": "http://localhost:8000/sse"
}
}
}
Command Line Options
-token: 1Panel access token-host: 1Panel access address-transport: Transport type (stdio or sse, default: stdio)-addr: Start SSE server address (default: http://localhost:8000)
Available Tools
The server provides various tools for interacting with 1Panel:
| Tool | Category | Description |
|---|---|---|
| get_dashboard_info | System | List dashboard status |
| get_system_info | System | Get system information |
| list_websites | Website | List all websites |
| create_website | Website | Create a website |
| list_ssls | Certificate | List all certificates |
| create_ssl | Certificate | Create a certificate |
| list_installed_apps | Application | List installed apps |
| install_openresty | Application | Install OpenResty |
| install_mysql | Application | Install MySQL |
| list_databases | Database | List all databases |
| create_database | Database | Create a database |
関連サーバー
Prismic
An MCP server for interacting with the Prismic headless CMS.
AWS MCP Servers
A suite of MCP servers providing AI applications with access to AWS documentation, contextual guidance, and best practices.
CMP MCP Server
An MCP server for CMP API integration, built to run on Cloudflare Workers.
Vertex AI MCP Server
Interact with Google Cloud's Vertex AI Gemini models for coding assistance and general query answering.
Azure Pricing MCP Server
Query Azure retail pricing information using the Azure Retail Prices API.
Remote MCP Server
A production-ready MCP server on Cloudflare Workers with GitHub OAuth and Fantasy Premier League integration.
MCP Deployment AWS
A guide and example code for deploying MCP servers cost-effectively on AWS and integrating them with AI agent frameworks.
K8s MCP Server
A server for Kubernetes CLI tools like kubectl, istioctl, helm, and argocd, supporting multi-cluster management via dynamic kubeconfig.
AI Image MCP Server
AI-powered image analysis using OpenAI's Vision API.
Simple OpenStack MCP
Execute OpenStack CLI commands using LLMs. Requires a configured OpenStack CLI environment.