About Plesk
Plesk MCP Server lets administrators manage Plesk hosting servers through AI agents and apps. Built on the Plesk and WP Toolkit REST APIs, it runs locally and supports core administration, shell commands, and file uploads.
Key features
- 01Manage Plesk servers
- 02Use the WP Toolkit REST API
- 03Run shell commands
- 04Upload files to servers
- 05Run the MCP server locally
Use cases
- 01Manage Plesk hosting through an AI agent
- 02Handle server tasks with shell commands
- 03Upload files to a server
MCP support
It exposes Plesk administration capabilities to MCP clients, including core management, shell commands, and file uploads. The server runs locally and operates through the Plesk REST API and WP Toolkit REST API.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx plesk-mcpPLESK_HOSTBase URL of your Plesk server. May include port. Example: https://plesk.example.com:8443PLESK_API_KEYSecretPlesk API key. Create via `plesk bin secret_key --create -description 'Plesk MCP'` on the server. Required, unless PLESK_USERNAME and PLESK_PASSWORD are provided.PLESK_USERNAMEUsername for authenticating with your Plesk server. Typically "admin".PLESK_PASSWORDSecretPassword for authenticating with your Plesk server.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEPlesk MCP Server
This MCP server for Plesk allows administrators to manage their Plesk servers using various AI agents and apps. It builds on top of Plesk REST API and WP Toolkit REST API, and provides core administration capabilities, as well as ability to manage the server through shell commands and upload files to the server.
The MCP server runs locally on your machine, so important information doesn't leave your environment.
Plesk Requirements
The MCP server is expected to support any sufficiently recent Plesk version (there are no strict limitations) and any OS (Linux or Windows) that Plesk supports. However, it was tested only on Plesk Obsidian 18.0.76, so prefer using a supported Plesk version.
Obviously, API access must not be disabled on the server.
MCP Server Requirements
You will need uv Python package manager to run the server. Refer to the official documentation for installation instructions.
Usage
Configure the server in your VS Code mcp.json or equivalent (in other agents or apps) using a configuration like:
{
"servers": {
"plesk": {
"command": "uvx",
"args": [
"plesk-mcp@latest"
],
"env": {
// Base URL of your Plesk server. May include port.
// If you don't have a valid TLS certificate or want to use HTTP,
// add the --insecure flag to the args above.
// However, this is not recommended as you credentials may be leaked as a result.
"PLESK_HOST": "https://plesk.example.net:8443",
// API key (recommended).
// Create via `plesk bin secret_key --create -description 'Plesk MCP'` on the server.
"PLESK_API_KEY": "00000000-0000-0000-0000-000000000000",
// Alternatively, you can use username and password.
"PLESK_USERNAME": "admin",
"PLESK_PASSWORD": "passwd"
}
}
}
}
You may want to use env file (e.g. via "envFile" parameter) if your agent or app supports it. This will avoid putting credentials directly in the config file.
See uvx plesk-mcp@latest --help for details on available options and environment variables.
Recommended Usage
For better behavior, it's recommended to use this MCP server in combination with a documentation MCP server. Select either plesk-local-docs-mcp or plesk-remote-docs-mcp. This will allow the agent to get more accurate information about Plesk usage when needed.
You may also attach several Plesk servers at once if needed (e.g. for managing multiple servers).
Here's an example configuration:
{
"servers": {
"plesk-docs": {
"command": "uvx",
"args": [
"plesk-local-docs-mcp@latest"
],
"env": {
"OPENAI_API_KEY": "sk-..."
}
},
"plesk1": {
"command": "uvx",
"args": [
"plesk-mcp@latest"
],
"env": {
"PLESK_HOST": "https://plesk1.example.net:8443",
"PLESK_API_KEY": "00000000-0000-0000-0000-000000000000"
}
},
"plesk2": {
"command": "uvx",
"args": [
"plesk-mcp@latest"
],
"env": {
"PLESK_HOST": "https://plesk2.example.net",
"PLESK_USERNAME": "admin",
"PLESK_PASSWORD": "passwd"
}
}
}
}
Development
MCP server run command:
uv run plesk-mcp --log-level debug --insecure
Before commit:
uv run ruff format
uv run ruff check --fix
uv run mypy .
uv run pytest
Publish:
uv build --clear
uv publish
mcp-publisher login github
mcp-publisher publish
Testing
Using Plesk Docker Image
If you don't have a Plesk instance but want to test this MCP server, you may use Plesk Docker image instead:
docker run -d --rm --tmpfs /tmp --tmpfs /run --tmpfs /run/lock -v /sys/fs/cgroup:/sys/fs/cgroup --cgroupns host -p 80:80 -p 443:443 -p 8880:8880 -p 8443:8443 --name plesk plesk/plesk
The Docker image startup is not instant, so give it a minute or so before trying to connect.
And then configure the MCP server as:
{
"servers": {
"plesk": {
"command": "uvx",
"args": [
"plesk-mcp@latest",
"--insecure"
],
"env": {
"PLESK_HOST": "https://localhost:8443",
"PLESK_PASSWORD": "changeme1Q**"
}
}
}
}
Without Plesk Server (Demo Mode)
Alternatively, run in demo mode from sources (with mocked responses):
{
"servers": {
"plesk": {
"command": "uv",
"args": [
"run",
"plesk-mcp"
],
"env": {
"PLESK_HOST": "https://linux.demo.example.net",
"PLESK_API_KEY": "-"
}
}
}
}
Automated tests
Unit tests run with uv run pytest (in the project root and in each sub-project). Smoke tests that exercise real services are skipped by default and selected via -m smoke:
# Plesk MCP smoke tests (against a reachable Plesk instance, e.g. from the Docker image described above)
PLESK_HOST=https://localhost:8443 PLESK_PASSWORD='changeme1Q**' PLESK_INSECURE=1 \
uv run pytest -m smoke
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.