The DuckDuckGo Search MCP server provides a privacy-friendly, AI-enhanced web search and content extraction tool with the following capabilities:
Web Search: Perform searches using DuckDuckGo, with options to specify page number and number of results
Felo AI Search: Access Felo AI for technical information and advanced search capabilities, with streaming response options
Fetch URL Content: Extract and filter content from URLs, with controls for maximum length, tag exclusion, and inclusion of links/images/main content
URL Metadata Extraction: Retrieve metadata such as title and description from web pages
The server performs direct web scraping rather than relying on limited APIs and does not require API keys.
Enables web search functionality by scraping DuckDuckGo HTML results, providing more comprehensive search capabilities than limited APIs.
Allows the MCP server to be installed and run through the npm package registry, making it easily accessible for AI assistants.
Links to the OEvortex YouTube channel for updates and tutorials related to the MCP server.
DuckDuckGo Search MCP supports the Model Context Protocol (MCP) standard, making it compatible with various AI assistants and tools.
✨ Features
Unlike many search tools, this package performs actual web scraping rather than using limited APIs, giving you more comprehensive results.
Related MCP server: DuckDuckGo MCP Server
🚀 Quick Start
This will download and run the latest version of the MCP server directly without installation – perfect for quick use with AI assistants.
🛠️ Installation Options
Run globally:
🧑💻 Command Line Options
Use the--version flag to check which version you're running.
🤖 Using with MCP Clients
The most common way to use this tool is by integrating it with MCP-compatible AI assistants.
Add the server to your MCP client configuration:
Or if installed globally:
After configuring, restart your MCP client to apply the changes.
🧰 Tools Overview
📁 Project Structure
🤝 Contributing
Contributions are welcome! Please open issues or submit pull requests.
Please follow the existing code style and add tests for new features.
📺 YouTube Channel
📄 License
Apache License 2.0
This project is licensed under the Apache License 2.0 – see theLICENSE file for details.