MCP Node Duckduckgo

🚀 MCP Node DuckDuckGo Server

An application based on Node.js, running as an MCP (Modular Control Platform) server, offering two main tools:

• Search: Query DuckDuckGo and obtain formatted search results.
• Fetch Content: Scrape and parse text content from a specified web page URL.

🚀 Quick Start

The MCP Node DuckDuckGo Server is a Node.js - based server that provides DuckDuckGo search and web content scraping capabilities via an HTTP port. This project demonstrates:

• Using Express to create a server.
• Using Axios for HTTP requests.
• Using Cheerio to parse HTML.

✨ Features

• DuckDuckGo Search: Execute search queries using the POST API and return formatted DuckDuckGo results for further processing.
• Web Content Scraping: Retrieve and parse text content from a specified URL.
• Rate Limiting: Provide basic rate - limiting functionality to manage request frequency.
• Scalable MCP Server: Tools are organized modularly for easy addition or modification of features.

📦 Installation

Prerequisites

• Node.js (v12 or higher)
• npm

Steps

1. Clone the repository Clone the repository from GitHub:

   git clone <repository URL>
   

2. Navigate to the project folder

   cd mcp-node-duckduckgo-server
   

3. Install dependencies Use npm to install the required packages:

   npm install express axios cheerio
   

💻 Usage Examples

Basic Usage

Start the server

To start the server, run the following command:

node mcp-node-duckduckgo-server.js

You should see a log message similar to the following:

MCP server "ddg-search" is running on port 3000

List available tools

To list all available tools, open a new terminal window and run:

curl http://localhost:3000/tools

This will output a JSON list showing the registered tools (e.g., "search" and "fetchContent").

Use the search tool

To perform a search query using the search tool:

curl -X POST http://localhost:3000/run-tool -H "Content-Type: application/json" -d "{\"toolName\":\"search\",\"params\":{\"query\":\"Test query\",\"maxResults\":5}}"

The response will contain formatted search results from DuckDuckGo.

Use the content - fetching tool

To fetch content from a specified web page:

curl -X POST http://localhost:3000/run-tool -H "Content-Type: application/json" -d "{\"toolName\":\"fetchContent\",\"params\":{\"url\":\"https://www.channelnewsasia.com/singapore/ge2025-general-election-may-3-parliament-dissolved-5064316\"}}"

The server will return a text snippet extracted from the scraped web page.

🔧 Technical Details

• The server outputs informational and error logs to the terminal.
• Use these logs to troubleshoot issues such as timeouts, HTTP errors, or unexpected behavior in the responses.

🤝 Contribution Guidelines

Contributions are welcome! If you'd like to contribute:

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

📄 License

This project is licensed under the MIT License. Please refer to the LICENSE file for details.