Websearch

🚀 Web Search Guide

The WebSearch MCP server is a tool for performing web searches, supporting various advanced features such as excluding specific domains, specifying languages, and regions. Here is a detailed usage guide.

🚀 Quick Start

📦 Installation

Run the Service with Docker

You can quickly start the WebSearch MCP server using the following command:

docker-compose up --build

This command will build and run all necessary containers, including the WebSearch service and FlareSolverr (for handling anti-bot verification).

Manual Installation

1. Clone the repository:

git clone <repository-url>
cd websearch-mcp-server

2. Install dependencies:

npm install

3. Start the development mode:

npm run dev

✨ Features

The WebSearch MCP server offers the following features:

• Multilingual Support: Returns search results according to the specified language.
• Regional Restrictions: Filters results based on the region code.
• Exclude Domains: Specify domains to exclude to avoid displaying content from specific websites.
• Multiple Result Types: Supports three result types: "all", "news", and "blogs".

Example Response

{
  "query": "Machine learning trends",
  "results": [
    {
      "title": "Artificial intelligence development trends in 2025",
      "snippet": "Key artificial intelligence trends in 2025 include the application of multimodal AI, generative models, and quantum artificial intelligence in enterprises...",
      "url": "https://example.com/ml-trends-2025",
      "siteName": "Artificial Intelligence Research Today",
      "byline": "Dr. Jane Smith"
    },
    {
      "title": "The five-year evolution of machine learning: 2020 - 2025",
      "snippet": "Over the past five years, machine learning has evolved from supervised learning methods to more complex self-supervised and reinforcement learning paradigms...",
      "url": "https://example.com/ml-evolution",
      "siteName": "Tech Insights",
      "byline": "John Doe"
    }
  ]
}

💻 Usage Examples

As a Command-Line Tool

Run the following command to start the MCP server:

npm run start

Then interact with the server using the provided test client:

npm run test-client

As a Library

You can use this package programmatically:

import { createMCPClient } from '@modelcontextprotocol/sdk';

// Create an MCP client
const client = createMCPClient({
  transport: { type: 'subprocess', command: 'npx websearch-mcp' }
});

// Perform a web search
const response = await client.request({
  method: 'call_tool',
  params: {
    name: 'web_search',
    arguments: {
      query: 'Your search term',
      numResults: 5,
      language: 'zh'
    }
  }
});

console.log(response.result);

🔧 Troubleshooting

Web Search Service Issues

• Error Messages: Check for any error log outputs.
• Anti-Bot Verification: Ensure that FlareSolverr is running properly.

Development Issues

• Missing Dependencies: If the installation fails, re-run npm install.
• Build Failures: Check if the package.json file in the project is complete.

Project Structure

websearch-mcp-server/
├── src/                 # Source code directory
│   ├── index.js       # Entry file
│   └── server.js      # Server configuration
├── package.json       # Dependencies and scripts
└── docker-compose.yml # Docker configuration file

Publishing an npm Package

1. Update the version number in package.json.
2. Commit the changes:

git add .
git commit -m "Update version"

3. Package and publish:

npm pack
npm publish

Contribution Guidelines

• Please fork the repository and develop on your branch.
• Before submitting a Pull Request, ensure that the code passes all tests.

Thanks for using the WebSearch MCP server! If you have any questions, please feel free to contact the maintenance team.