MCP Python

🚀 MCP Server Demo

This is a demonstration implementation of a Model Context Protocol (MCP) server. The MCP protocol facilitates communication between clients and AI models, offering a standardized way to exchange prompts, context, and model responses.

🚀 Quick Start

Prerequisites

• Python 3.8 or higher
• pip or uv package manager

Setup

1. Clone this repository.
2. Create a virtual environment:

   python -m venv .venv
   

3. Activate the virtual environment:
   • Windows: .venv\Scripts\activate
   • Unix/macOS: source .venv/bin/activate
4. Install the dependencies:

   pip install -e .
   

Running the Server

python main.py

The server will start listening for client connections on the default port.

✨ Features

• Dynamic Greeting Resource: @mcp.resource("greeting://{name}") provides personalized greetings based on the given name.
• File Operation Tools:
  • list_files(directory_path: str) -> List[str]: Lists all files in the specified directory.
  • create_file(file_path: str, content: str = "") -> str: Creates a new file with optional initial content.
  • add_to_file(file_path: str, content: str) -> str: Appends content to an existing file.
  • read_file(file_path: str) -> str: Reads and returns the content of a file.
  • delete_file(file_path: str) -> str: Deletes the specified file.
  • search_in_file(file_path: str, search_term: str) -> str: Searches for a term in a file and returns the matching lines.
  • rename_file(old_path: str, new_path: str) -> str: Renames or moves a file.

📚 Documentation

Project Structure

• main.py: The entry point of the application.
• pyproject.toml: Project configuration and dependencies.
• uv.lock: Dependency lock file.

API

The server implements the Model Context Protocol specification, which includes:

• Request/response formats for model interaction.
• Context management.
• Authentication mechanisms.
• Rate limiting.

📄 License

Last Updated: April 24, 2025