Search Engines Proxy

🚀 Multi-Channel Proxy (MCP) Project Documentation

The Multi-Channel Proxy (MCP) is an innovative technology designed to enhance the information retrieval capabilities of AI assistants by integrating multiple search engines and network information sources. This system supports multiple search engines such as Brave, Metaso, and Bocha, and provides powerful search functions and result analysis tools.

🚀 Quick Start

📦 Installation

1. Clone the repository:

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

2. Install dependencies:

pip install -r requirements.txt

3. Initialize the configuration file:

python setup.py init-config

Environment Variable Setup

Create a .env file and add the following content:

BRAVE_API_KEY=your_brave_api_key_here
METASO_API_KEY=your_metaso_api_key_here
BOCHA_API_KEY=your_bocha_api_key_here

✨ Features

Core Components

1. MCP Server (server.py)
   • Provides RESTful API interfaces.
   • Responsible for coordinating task distribution and result aggregation of different search engines.
2. Search Engine Proxy (proxy/)
   • Includes three modules for Brave, Metaso, and Bocha, which handle search requests from each engine respectively.

Search Engine Implementations

Brave Search Module (brave/)

• client.py: Defines the core client for interacting with the Brave search API.
• config.py: Configures parameters and rate-limiting strategies.
• exceptions.py: Handles exceptions specific to Brave API calls.

Metaso Search Module (metaso/)

• client.py: Implements the communication logic with the Metaso search service.
• config.py: Defines configuration parameters and access control rules.
• exceptions.py: Manages error handling in Metaso API calls.

Bocha Search Module (bocha/)

• client.py: Provides an interface for interacting with the Bocha search engine.
• config.py: Configures and optimizes parameters for using the Bocha API.
• exceptions.py: Handles exceptions specific to the Bocha API.

💻 Usage Examples

Tool Configuration

1. Brave Search Tool (brave_search.py)
2. Metaso Search Tool (metaso_search.py)
3. Bocha Search Tool (bocha_search.py)

Operation Process

1. Start the MCP server:

python server.py start

2. Call the search interface:

• Send requests using the curl command or an HTTP client.

Basic Usage

# Send a GET request
curl http://localhost:8080/search?q=人工智能&engine=brave,metaso

The response will be in the following format:

{
  "status": "success",
  "results": [
    {
      "url": "https://example.com/1",
      "title": "AI基础教程",
      "snippet": "介绍机器学习基本概念..."
    },
    ...
  ]
}

🔧 Technical Details

Project Structure

search/
├── __init__.py
├── server.py              # MCP server implementation
└── proxy/                 # Search engine proxy
    ├── brave/             # Brave search module
    │   ├── __init__.py
    │   ├── client.py      # Core client implementation
    │   ├── config.py      # Configuration and rate limiting
    │   └── exceptions.py  # Exception definition
    ├── metaso/            # Metaso search module
    │   ├── __init__.py
    │   ├── client.py      # Core client implementation
    │   ├── config.py      # Configuration and rate limiting
    │   └── exceptions.py  # Exception definition
    └── bocha/              # Bocha search module
        ├── __init__.py
        ├── client.py       # Core client implementation
        ├── config.py       # Configuration and optimization parameters
        └── exceptions.py   # Error handling logic

Interface Definition

Request Format

{
  "query": "搜索关键词",
  "engine": ["brave", "metaso", "bocha"],
  "params": {
    // Optional parameters, such as sorting method, number of results, etc.
  }
}

Response Format

{
  "status": "success",
  "results": [
    {
      "url": "链接地址",
      "title": "标题",
      "snippet": "简要描述"
    },
    ...
  ]
}

📚 Documentation

Important Note

• Ensure the security of API keys and avoid leakage.
• Regularly update dependency libraries to get the latest features and security patches.

Through the above documentation, you can learn in detail how to set up and use the MCP project to enhance the information retrieval capabilities of AI assistants.