MCP Server Of9

🚀 MCP Server

An MCP (Model Context Protocol) server offering a variety of tools for AI agents and Large Language Models (LLMs), including web search powered by SearXNG and file system operations.

🚀 Quick Start

Quick Start Implementation

# Use the built-in MCP server instance
from mcp_server.server import mcp

@mcp.tool()
def my_custom_tool(param1: str, param2: int = 10) -> dict:
    """My custom tool description"""
    # Implement tool functionality
    return {"result": f"Processed {param1} with {param2}"}

Native Architecture Implementation

Refer to the Developer Guide to learn how to add custom tools using the native architecture.

✨ Features

• Web Search: Perform web searches with custom parameters using SearXNG.
• File System Operations: Read, write, and manage files with security controls.
• Scalable Architecture: Support for adding custom tools compliant with the MCP protocol.
• Docker Support: Recommended to run the server and related services via Docker.

📦 Installation

Requirements

• Python 3.13 or higher
• uv package manager (for direct installation)

Docker Installation (Recommended)

# Build the Docker image
docker build -t mcp-server .

# Start the server and SearXNG service
docker-compose up

Direct Installation

# Ensure Python 3.13 is installed
python --version  # Should show something like Python 3.13.x

# Install uv if not already installed
pip install uv

# Create a virtual environment and install dependencies
uv venv --python=python3.13
uv install

# Start the server
python -m mcp_server start --config config.env

💻 Usage Examples

Modern Client Example

from mcp_client.session import ClientSession

# Initialize the client session
session = ClientSession('http://localhost:8000')

# Call a tool
response = session.call_tool('my_custom_tool', param1='test')
print(response)

Simple Client Example

import requests

# Directly call the server API
url = 'http://localhost:8000/api'
data = {
    'tool': 'my_custom_tool',
    'params': {'param1': 'test'}
}
response = requests.post(url, json=data)
print(response.json())

📚 Documentation

Tool Explanation

• Web Search: Achieve efficient and secure web searches through SearXNG.
• File System Operations: Support read, write, and delete operations on files with permission controls.
• Scalability: Easily integrate new MCP protocol tools and services.

Environment Variable Configuration

# Example configuration file content
MCP_SERVER__HOST=0.0.0.0
MCP_SERVER__PORT=8000
MCP_SEARXNG__INSTANCE_URL=http://localhost:8080/

Client Examples Location

• The examples/ directory contains client examples:
  • examples/client.py: A modern client using the ClientSession API.
  • examples/simple_client.py: A simple client directly calling the API.

Extension Development

Using the Quick MCP Method

from mcp_server.server import mcp

@mcp.tool()
def my_custom_tool(param1: str, param2: int = 10) -> dict:
    """My custom tool description"""
    # Implement tool functionality
    return {"result": f"Processed {param1} with {param2}"}

Using the Native Architecture

Refer to the Developer Guide to learn how to add more features using the native architecture.

📄 License

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

Acknowledgments

• Model Context Protocol provides the protocol specification.
• SearXNG provides the implementation of the search function.