Provides semantic search capabilities over the Plesk Extensions Guide documentation, allowing users to retrieve relevant information about extension development through natural language queries.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Plesk Extensions Guide MCP ServerHow do I add a custom button to the Plesk interface?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Plesk Extensions Guide MCP Server
A Model Context Protocol (MCP) server that provides semantic search capabilities over the Plesk Extensions Guide documentation using Retrieval-Augmented Generation (RAG).
Overview
This MCP server indexes and searches Plesk extension development documentation using vector embeddings. It allows AI assistants and applications to retrieve relevant information from the Plesk Extensions Guide through natural language queries.
Features
Semantic Search: Search documentation using natural language queries
Vector Embeddings: Uses OpenRouter's text-embedding-3-small model for intelligent document matching
ChromaDB Storage: Efficient vector database for fast retrieval
Automatic Documentation Download: Easy setup with automated documentation fetching
Prerequisites
Python 3.12 or higher
pippackage managerOPENROUTER_API_KEYenvironment variable (for embeddings)
Installation
Clone the repository:
git clone https://github.com/barateza/mcp-plesk-extension-guide.git cd mcp-plesk-extension-guideCreate a virtual environment:
python -m venv .venv source .venv/bin/activate # macOS/Linux # OR .venv\Scripts\activate # WindowsInstall dependencies:
pip install -e .
Setup
1. Download Documentation
The MCP server requires the Plesk Extensions Guide documentation. Download and extract it using the provided script:
This script will:
Download the documentation ZIP from Plesk's documentation server
Extract it to the
html/folderCreate the
storage/directory for the vector database
2. Configure API Key
Set your OpenRouter API key as an environment variable:
Or add it to a .env file in the project root (this file should not be committed to version control).
Usage
The MCP server exposes two main tools for interacting with the Plesk Extensions Guide:
1. search_extensions_guide
Search the indexed documentation with a semantic query.
Parameters:
query(string): Your search query in natural language
Example:
2. index_documentation
Scan and index all documentation files. This is called automatically on first run, but can be called again to re-index.
Parameters: None
Example:
Configuration
The server uses the following environment variables:
Variable | Description | Required |
| API key for OpenRouter embeddings service | Yes |
| ChromaDB implementation (default: duckdb+parquet) | No |
Architecture
server.py: FastMCP server implementation with indexing and search tools
main.py: Entry point for running the server
scripts/download_docs.py: Documentation download utility
html/: Extracted Plesk Extensions Guide documentation (created after setup)
storage/: Vector database storage (created automatically on first run)
Development
See CONTRIBUTING.md for development guidelines and how to contribute.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Documentation
For more information about Plesk extension development, visit:
Support
If you encounter any issues:
Ensure Python 3.12+ is installed
Verify your
OPENROUTER_API_KEYis set correctlyRun
python scripts/download_docs.pyagain to refresh documentationCheck that
html/andstorage/directories were created successfully
For bugs or feature requests, please open an issue on GitHub.