What is Mcp And Adk

MCP-ADK is a Python-based toolkit that enables the development of intelligent agents capable of extracting and processing information from Wikipedia articles using the Message Context Protocol (MCP). It facilitates real-time interactions and rich content extraction, making it suitable for applications that require up-to-date information from Wikipedia.

Use cases

MCP-ADK can be used in various scenarios such as chatbots that provide Wikipedia summaries, educational tools for students to gather information quickly, research assistants that extract relevant articles, and any other applications that benefit from dynamically pulling content from Wikipedia.

How to use

To use MCP-ADK, you first need to clone the repository and set up a virtual environment. After installing the required packages, you can start the server using a command. The API facilitates real-time communication through SSE and provides endpoints to manage messages effectively. Developers can also integrate the agent into their applications by using the provided API interface.

Key features

Key features of MCP-ADK include Wikipedia article extraction and markdown conversion, real-time communication via Server-Sent Events (SSE), robust error handling, a clean API interface, and asynchronous processing capabilities, enabling efficient and effective agent development.

Where to use

MCP-ADK can be deployed in various environments such as web applications, desktop applications, and educational platforms where real-time data extraction and processing of Wikipedia content is beneficial. It is particularly useful in any setting that requires interaction with users and dynamic content delivery.

🚀 MCP-ADK (Message Context Protocol - Agent Development Kit)

A Python-based toolkit for building and managing agents with Wikipedia article extraction capabilities.

📋 Overview

MCP-ADK is a small demo to showcase the capability of Message Context Protocol (MCP) with an Agent Development Kit (ADK) to create intelligent agents capable of processing and extracting information from Wikipedia articles. The project provides a robust server implementation with real-time communication capabilities using Server-Sent Events (SSE).

✨ Features

• 📚 Wikipedia article extraction and conversion to markdown
• 🔄 Real-time communication using Server-Sent Events (SSE)
• 🛡️ Robust error handling and validation
• 🎯 Clean and modern API interface
• ⚡ Asynchronous processing capabilities

🛠️ Requirements

• Python >= 3.10
• Dependencies (automatically installed with the package):
  • beautifulsoup4
  • deprecated
  • google-adk
  • html2text
  • mcp[cli]
  • requests

🚀 Installation

1. Clone the repository:

git clone https://github.com/yourusername/mcp-adk.git
cd mcp-adk

2. Create and activate a virtual environment:

uv venv
source .venv/bin/activate
uv init

3. Install the package by adding them in pyproject.toml:

uv add "beautifulsoup4==4.12.3"

💻 Usage

🖥️ Starting the Server

Run the server using:

uv run server.py

The server will start on localhost:8001.

🔍 Using MCP Inspector

uv run mcp dev server.py

🌐 Launching ADK Server

After stopping MCP Inspector, launch the ADK server:

uv run adk web

🔌 API Endpoints

• /sse - Server-Sent Events endpoint for real-time communication
• /messages/ - Endpoint for posting messages

📝 Example Usage

from mcp_adk import agent

# Example code for using the agent
# (Add specific examples based on your implementation)

📁 Project Structure

mcp-adk/
├── adk-agent/          # Agent implementation
├── server.py           # Main server implementation
├── main.py            # Entry point
├── pyproject.toml     # Project configuration
└── README.md          # This file