Model-Context-Protocol

Overview

This project provides a comprehensive Model Context Protocol client implementation in Python. It enables Large Language Models to connect with external tools through either stdio or SSE (Server-Sent Events) transport protocols. The architecture supports multi-turn conversations and uses Gemini for intelligent orchestration of tool calls. The client includes both CLI and web UI interfaces with FastAPI, allowing users to configure servers, manage API keys, and monitor tool execution through a browser interface.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

Comparable tools

Installation

# Clone and install dependencies
git clone https://github.com/Abdulabin/Model-Context-Protocol.git
cd Model-Context-Protocol
pip install -r requirements.txt

# Configure API keys
# Create .env file with GEMINI_API_KEY="YOUR_API_KEY_HERE"

# Run CLI client
python mcp_client.py

# Start web UI
uvicorn app:app

"mcpServers": {
  "python-client": {
    "command": "python",
    "args": ["/path/to/Model-Context-Protocol/mcp_client.py"]
  }
}

FAQ

What transport protocols are supported?

The client supports both stdio for local process-based servers and SSE (Server-Sent Events) for remote HTTP-based servers.

Can I connect to multiple MCP servers simultaneously?

Yes, the architecture supports multi-server connectivity, allowing you to connect to multiple MCP servers at the same time.

Compare Model-Context-Protocol with