MCP cover image
See in Github
2025-03-03

Serveur MCP avec DuckDucksEarch, Web2MD et Web2photo

1

Github Watches

1

Github Forks

0

Github Stars

MCP DuckDuckResearch

An MCP (Model Context Protocol) server that combines DuckDuckGo search capabilities with web page content extraction and screenshot functionality. This server bridges the gap between searching for information and accessing web content programmatically.

Features

  • 🔍 DuckDuckGo Search: Search the web using DuckDuckGo's search engine
  • 📄 Content Extraction: Visit web pages and extract their content as Markdown
  • 📸 Screenshot Capture: Take screenshots of web pages with automatic size optimization
  • Robust Error Handling: Built-in protection against bot detection and content validation
  • 🔒 Safe Search Options: Configurable safe search levels for appropriate content filtering

Installation

# Clone the repository
git clone https://github.com/yourusername/mcp-duckduckresearch.git
cd mcp-duckduckresearch

# Install dependencies
npm install

# Build the project
npm run build

Usage with Cline and Roo Code

Installation for Cline

  1. Build the project first using the installation steps above

  2. Configure the MCP server in your Cline settings:

    Edit your Cline MCP settings file at: %APPDATA%\Code\User\globalStorage\rooveterinaryinc.roo-cline\settings\cline_mcp_settings.json

    Add the following configuration:

    {
      "mcpServers": {
        "duckduckmcp": {
          "command": "node",
          "args": ["path/to/mcp-duckduckresearch/build/index.js"],
          "disabled": false,
          "alwaysAllow": []
        }
      }
    }
    

    Replace path/to/mcp-duckduckresearch with the actual path where you cloned this repository.

Available Tools

Once configured, the following tools will be available in Roo Code:

1. search_duckduckgo

Search the web using DuckDuckGo. Example usage in Roo Code:

<use_mcp_tool>
<server_name>duckduckmcp</server_name>
<tool_name>search_duckduckgo</tool_name>
<arguments>
{
  "query": "typescript best practices",
  "options": {
    "region": "zh-cn",
    "safeSearch": "MODERATE",
    "numResults": 10
  }
}
</arguments>
</use_mcp_tool>

2. visit_page

Visit a webpage and extract its content as Markdown:

<use_mcp_tool>
<server_name>duckduckmcp</server_name>
<tool_name>visit_page</tool_name>
<arguments>
{
  "url": "https://example.com",
  "takeScreenshot": false
}
</arguments>
</use_mcp_tool>

3. take_screenshot

Take a screenshot of the currently loaded page:

<use_mcp_tool>
<server_name>duckduckmcp</server_name>
<tool_name>take_screenshot</tool_name>
<arguments>
{}
</arguments>
</use_mcp_tool>

Example Workflow in Roo Code

Here's a complete example of searching for information and visiting a result:

  1. First, search for information:
<use_mcp_tool>
<server_name>duckduckmcp</server_name>
<tool_name>search_duckduckgo</tool_name>
<arguments>
{
  "query": "TypeScript best practices",
  "options": {
    "numResults": 10,
    "safeSearch": "MODERATE"
  }
}
</arguments>
</use_mcp_tool>
  1. Then, visit one of the results:
<use_mcp_tool>
<server_name>duckduckmcp</server_name>
<tool_name>visit_page</tool_name>
<arguments>
{
  "url": "https://example.com/typescript-practices",
  "takeScreenshot": true
}
</arguments>
</use_mcp_tool>

The server will automatically handle:

  • Browser initialization and cleanup
  • Content extraction and conversion to Markdown
  • Screenshot capture and optimization
  • Error handling and retries

Development

Prerequisites

  • Node.js (v18 or higher)
  • npm
  • A system capable of running Chrome/Chromium (for Playwright)

Setup Development Environment

# Install dependencies
npm install

# Start in development mode
npm run dev

# Run tests
npm test

# Run tests with coverage
npm run test:coverage

# Format code
npm run format

# Lint code
npm run lint

Project Structure

mcp-duckduckresearch/
├── src/
│   ├── browser.ts     # Browser management and content extraction
│   ├── search.ts      # DuckDuckGo search implementation
│   ├── types.ts       # Type definitions and schemas
│   ├── utils.ts       # Utility functions
│   └── index.ts       # Main server implementation
├── tests/
│   ├── unit/          # Unit tests
│   └── integration/   # Integration tests
└── package.json       # Project configuration

Testing

The project uses Vitest for testing. Tests are organized into:

  • Unit Tests: Testing individual components and functions
  • Integration Tests: Testing the complete workflow
  • Test Coverage: Aiming for >80% coverage

Run tests with:

# Run all tests
npm test

# Run with coverage
npm run test:coverage

Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

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

Credits

相关推荐

  • NiKole Maxwell
  • I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

  • https://jgadvisorycpa.com
  • This GPT assists in finding a top-rated business CPA - local or virtual. We account for their qualifications, experience, testimonials and reviews. Business operators provide a short description of your business, services wanted, and city or state.

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • apappascs
  • Découvrez la collection la plus complète et la plus à jour de serveurs MCP sur le marché. Ce référentiel sert de centre centralisé, offrant un vaste catalogue de serveurs MCP open-source et propriétaires, avec des fonctionnalités, des liens de documentation et des contributeurs.

  • ShrimpingIt
  • Manipulation basée sur Micropython I2C de l'exposition GPIO de la série MCP, dérivée d'Adafruit_MCP230XX

  • OffchainLabs
  • Aller la mise en œuvre de la preuve de la participation Ethereum

  • huahuayu
  • Une passerelle API unifiée pour intégrer plusieurs API d'explorateur de blockchain de type étherscan avec la prise en charge du protocole de contexte modèle (MCP) pour les assistants d'IA.

  • modelcontextprotocol
  • Serveurs de protocole de contexte modèle

    Reviews

    4 (1)
    Avatar
    user_9FVak8sp
    2025-04-17

    As a dedicated user of mcp, I am thoroughly impressed with mcp-duckduckresearch by bkataru-workshop. This seamless tool enhances research efficiency with its intuitive design and robust functionality. It simplifies complex queries and provides precise, reliable results that are vital for my projects. A must-have for any serious researcher!