Web Search Duckduckgo

🚀 DuckDuckGo Web Search MCP Server

This project offers an MCP (Model Context Protocol) server that enables you to conduct web searches using the DuckDuckGo search engine and optionally retrieve and summarize the content of the found URLs.

✨ Features

• Web Search: Conduct web searches using DuckDuckGo.
• Result Extraction: Extract titles, URLs, and excerpts from search results.
• Content Retrieval (Optional): Retrieve the content of URLs found in search results and convert it to Markdown format using the Jina API.
• Parallel Retrieval: Retrieve multiple URLs in parallel to speed up processing.
• Error Handling: Gracefully handle timeouts and other potential errors during search and retrieval.
• Configurable: Allows you to set the maximum number of search results to return.
• Jina API: Use the Jina API to convert HTML to Markdown.
• MCP Compatible: This server is designed to work with any MCP-compatible client.

🚀 Quick Start

Prerequisites

• uvx package manager

Claude Desktop Configuration

• If you're using Claude Desktop, you can add this server to the claude_desktop_config.json file.

{
    "mcpServers": {
        "web-search-duckduckgo": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/kouui/web-search-duckduckgo.git@main",
                "main.py"
            ]
        }
    }
}

⚠️ Important Note

The above configuration may not work properly. You may need to clone the repository to your local machine and use the following configuration.

{
    "mcpServers": {
        "web-search-duckduckgo": {
            "command": "uv",
            "args": [
                "--directory",
                "/path/to/web-search-duckduckgo",
                "run",
                "main.py"
            ]
        }
    }
}

Tools

• In your MCP client (e.g., Claude), you can now use the following tools:

• search_and_fetch: Search the web and retrieve the content of URLs.

  • query: The query string to search for.
  • limit: The maximum number of results to return (default: 3, maximum: 10).

• fetch: Retrieve the content of a specific URL.

  • url: The URL to retrieve.

📄 License

This project is licensed under the MIT License.