PMCP - Perfect Model Context Protocol Server
A comprehensive production-ready MCP server with AI integration, plugin management, and web-based administration. Features multi-database support, RAG capabilities, SSH/SFTP access, and a built-in plugin hub for managing the MCP ecosystem.
README
PMCP - Perfect Model Context Protocol Server
A comprehensive, production-ready Model Context Protocol (MCP) server with advanced AI capabilities, web-based administration, and extensive plugin ecosystem support.
š Features
Core Capabilities
- š¤ AI Integration: Support for OpenAI, Anthropic, and Google Gemini models
- š MCP Plugin Hub: Discover, install, and manage MCP plugins with ease
- š¾ Multi-Database Support: Redis for caching, MongoDB for persistence
- š Web Admin Interface: Comprehensive dashboard for server management
- š SSH/SFTP Access: Secure file operations and remote access
- š Real-time Monitoring: Live metrics, logs, and system status
Advanced Services
- š§ Memory Management: Persistent context and session handling
- š RAG (Retrieval-Augmented Generation): Document indexing and semantic search
- š Code Analysis: AI-powered code review and improvement suggestions
- š Playwright Integration: Web automation and browser control
- š Sequential Thinking: Chain-of-thought reasoning capabilities
Administration & Monitoring
- š Dashboard: Real-time system metrics and performance monitoring
- šļø File Management: Web-based file browser and editor
- š„ User Management: Authentication and access control
- š§ Configuration: Dynamic settings management
- š Logging: Comprehensive structured logging with multiple outputs
š ļø Quick Start
Prerequisites
- Python 3.8 or higher
- Redis server
- MongoDB server
- Git
Installation
-
Clone the repository
git clone https://github.com/NoobyNull/PMCP.git cd PMCP -
Set up Python environment
python3 -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate pip install -r requirements.txt -
Configure databases
# Install and start Redis sudo apt-get install redis-server sudo systemctl start redis-server # Install and start MongoDB sudo apt-get install mongodb sudo systemctl start mongodb -
Configure the server
cp config/server.yaml.example config/server.yaml # Edit config/server.yaml with your settings -
Start the server
# Development mode python admin_server.py # Production mode (systemd service) sudo ./setup_service.sh
Access Points
- Admin Interface: http://localhost:8080
- API Server: http://localhost:8000
- SSH/SFTP: localhost:2222
š Documentation
Quick Setup Guides
- š Deployment Guide - Production deployment instructions
- š§ Admin Interface Guide - Web interface overview
- š MCP Hub Guide - Plugin management
- š¤ Augment Integration - AI assistant setup
Advanced Configuration
- š LAN Access Setup - Network configuration
- š Service Management - Systemd service setup
- š Logging Configuration - Log management
- šØ UI/UX Customization - Interface theming
š MCP Plugin Ecosystem
PMCP includes a built-in plugin hub that provides access to the Model Context Protocol ecosystem:
Featured Plugins
- Filesystem MCP Server - Secure file system operations
- GitHub MCP Server - Repository management and operations
- Brave Search MCP Server - Web search capabilities
- SQLite/PostgreSQL MCP Servers - Database operations
- And many more...
Plugin Management
- Browse and search available plugins
- One-click installation with progress tracking
- Automatic dependency management
- Plugin status monitoring and updates
šļø Architecture
PMCP Server
āāā Admin Interface (Port 8080)
ā āāā Dashboard & Monitoring
ā āāā Plugin Management
ā āāā File Browser
ā āāā Configuration
āāā API Server (Port 8000)
ā āāā MCP Protocol Endpoints
ā āāā AI Service Integration
ā āāā Memory & Context Management
ā āāā RAG & Document Processing
āāā SSH/SFTP Server (Port 2222)
ā āāā Secure File Access
ā āāā Remote Command Execution
āāā Background Services
āāā Plugin Manager
āāā Database Connections
āāā Logging System
āāā Monitoring Agents
š¤ Contributing
We welcome contributions! Please see our Contributing Guidelines for details.
Development Setup
- Fork the repository
- Create a feature branch:
git checkout -b feature-name - Make your changes and add tests
- Run the test suite:
pytest - Submit a pull request
š License
This project is licensed under the MIT License - see the LICENSE file for details.
š Acknowledgments
- Model Context Protocol - The open standard this server implements
- FastAPI - The web framework powering our APIs
- Bootstrap - UI framework for the admin interface
- The MCP community for their excellent plugins and contributions
š Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Documentation: Project Wiki
PMCP - Empowering AI assistants with comprehensive context and capabilities š
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.