Nickclyde Duckduckgo MCP Server

🚀 DuckDuckGo Search-based MCP Server

A Model Context Protocol (MCP) server that offers DuckDuckGo web search capabilities, along with additional content scraping and parsing features.

✨ Features

• Web Search: Conduct advanced searches on DuckDuckGo with rate limiting and result formatting.
• Content Scraping: Fetch and parse web page content with intelligent text extraction.
• Rate Limiting: Built-in protection mechanism to prevent excessive search and content scraping rates.
• Error Handling: Comprehensive error capturing and logging.
• Output Format for LLMs: Results presented in a format specifically designed for large language models.

📦 Installation

Install via Smithery

Use Smithery to automatically install the DuckDuckGo search server for Claude Desktop:

npx -y @smithery/cli install @nickclyde/duckduckgo-mcp-server --client claude

Direct Installation via uv

Install directly from PyPI using uv:

uv pip install duckduckgo-mcp-server

💻 Usage Examples

Running on Claude Desktop

1. Download Claude Desktop.
2. Create or edit your Claude Desktop configuration file:
   • On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • On Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the following content to the configuration file:

{
    "mcpServers": {
        "ddg-search": {
            "command": "uvx",
            "args": ["duckduckgo-mcp-server"]
        }
    }
}

3. Restart Claude Desktop.

Using in a Development Environment

When developing locally, you can use the MCP CLI:

# Run with MCP Inspector
mcp dev server.py

# Install for testing with Claude Desktop
mcp install server.py

Available Tools

1. Search Tool

async def search(query: str, max_results: int = 10) -> str

Perform a web search on DuckDuckGo and return formatted results.

Parameters:

• query: The search query string.
• max_results: The maximum number of results to return (default is 10).

Returns: A formatted string containing titles, links, and excerpts.

2. Content Scraping Tool

async def fetch_content(url: str) -> str

Fetch and parse web page content from the specified URL and return the result in text format.

Parameters:

• url: The URL of the content to scrape.

Returns: The extracted plain text content.

📚 Documentation

Search Functionality

• Supports asynchronous requests for improved efficiency.
• Built-in rate limiting to prevent API call overload.
• Results are automatically formatted for easy subsequent processing.

Content Scraping Functionality

• Can fetch web page content from a specified URL.
• Equipped with an error handling mechanism to return friendly error messages when access is unavailable.
• Supports multiple content parsing methods to adapt to different web page structures.

Usage Examples

Search Example

result = await search("Python programming")
print(result)

The output might look like this:

Title: Python programming - Wikipedia
Link: https://zh.wikipedia.org/wiki/Python_(programming_language)
Excerpt: Python is a high-level programming language known for its readability.
...

Content Scraping Example

content = await fetch_content("https://www.example.com")
print(content)

The output might look like this:

This is an example web page content. Welcome to our website!

🤝 Contribution Guidelines

We welcome contributions from the community. Here are some potential areas for improvement:

• Add more search parameters (e.g., filtering conditions, sorting options).
• Optimize the content scraping algorithm to improve parsing accuracy.
• Implement a caching mechanism to enhance the efficiency of repeated requests.
• Support multi-language content processing.
• Increase the detail level of error handling logs.

Please contribute by submitting GitHub issues or Pull Requests.