MCP Servers Multi Agent Ai Infrastructure

🚀 MCP Server Multi-Agent AI Infrastructure

A comprehensive infrastructure for enabling a multi-agent AI swarm powered by a dedicated Model Context Protocol (MCP) server. This mono-repo contains the full component stack needed to enable collaboration, connectivity, and empower intelligent agents with various specializations.

🚀 Quick Start

Prerequisites

• Docker and Docker Compose
• Node.js (for local development)
• Python 3.9+ (for running clients and scripts)

Quick Start Steps

1. Download the project repository:

   git clone https://github.com/your-repository.git
   

2. Install dependencies:

   cd mcp-server && pip install -r requirements.txt
   cd ../inspector && npm install
   

3. Start the MCP server:

   python server.py
   

4. Start the inspector in a new terminal:

   cd inspector && npm run dev
   

✨ Features

This project enables the creation of a multi-agent AI ecosystem where specialized agents can collaborate, share context, and leverage diverse capabilities, communicating via the standardized Model Context Protocol (MCP). By providing a standardized communication layer, agents can seamlessly access vector databases, specialized tools, and various data sources.

The infrastructure supports:

• Semi-supervised search and retrieval via vector embeddings
• Multi-agent collaboration and communication
• Modular, microservices architecture
• Visual inspection and debugging of agent interactions
• Scalable tool framework for AI capabilities

📦 Core Components

Inspector

An interactive dashboard for monitoring, testing, and debugging MCP servers. Built with a React/Vite frontend and an Express backend.

• Location: /inspector
• Features:
  • Real-time connection to any MCP server
  • Interactive exploration of available tools
  • Testing of prompts and tool calls
  • Monitoring of agent interactions
  • Debugging of server responses and behavior

Qdrant-DB with MCP Integration

A vector database implemented with Qdrant, with full MCP server integration, providing semantic search capabilities for AI agents.

• Location: /qdrant-db
• Features:
  • Vector embeddings for semantic similarity search
  • Document storage with metadata
  • Python client for advanced operations
  • FastEmbed integration for efficient embeddings
  • Seamless connection with the MCP ecosystem

MCP Docker Network Infrastructure

Infrastructure for orchestrating and connecting MCP services in a unified network.

• Location: /mcp-docker-network
• Features:
  • Dedicated network for secure service communication
  • Container orchestration management tools
  • Service discovery within the swarm
  • Simplified deployment of complex agent systems

🛠️ Development

Each component can be developed independently:

• Inspector: React/TypeScript frontend and Express backend
• Qdrant MCP Server: Python FastMCP implementation
• Network Management: Bash scripts and Docker Compose configurations

Please refer to the README in each subdirectory for specific development instructions.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.