What is Mcp Duckduckgo Search

mcp-duckduckgo-search is a Model Context Protocol (MCP) server designed to integrate DuckDuckGo’s search capabilities with large language models (LLMs), providing extensive web search functionality with various result types and filtering options.

Use cases

Use cases include enhancing chatbots with real-time search capabilities, providing search functionalities in educational tools, assisting researchers in gathering information, and integrating search features in applications that require up-to-date content.

How to use

To use mcp-duckduckgo-search, configure your MCP client with the required settings, including your SerpAPI key. You can then perform web searches by sending a query to the ddg_search API endpoint.

Key features

Key features include comprehensive web search using DuckDuckGo, support for rich result types (knowledge graph, organic results, news, videos, images, related searches), region-specific search, configurable safe search levels, date-based filtering, pagination support, and built-in result caching.

Where to use

mcp-duckduckgo-search can be used in various fields such as research, content creation, data analysis, and any application requiring web search capabilities integrated with LLMs.

mcp-duckduckgo-search

⚠️ Notice

This repository is no longer maintained.

The functionality of this tool is now available in mcp-omnisearch, which combines multiple MCP tools in one unified package.

Please use mcp-omnisearch instead.

A Model Context Protocol (MCP) server for integrating DuckDuckGo
search capabilities with LLMs. This server provides comprehensive web
search functionality with support for various result types and
filtering options.

Features

• 🔍 Comprehensive web search using DuckDuckGo’s search engine
• 📊 Rich result types including:
  • Knowledge graph information
  • Organic search results
  • News articles
  • Video content
  • Image results
  • Related searches
• 🌍 Region-specific search support
• 🛡️ Configurable safe search levels
• 📅 Date-based filtering options
• 📄 Pagination support
• 💾 Built-in result caching
• 🔒 Safe search options (off, moderate, strict)

Configuration

This server requires configuration through your MCP client. Here are
examples for different environments:

Cline Configuration

Add this to your Cline MCP settings:

{
  "mcpServers": {
    "mcp-duckduckgo-search": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-duckduckgo-search"
      ],
      "env": {
        "SERPAPI_KEY": "your-serpapi-api-key"
      }
    }
  }
}

Claude Desktop with WSL Configuration

For WSL environments, add this to your Claude Desktop configuration:

{
  "mcpServers": {
    "mcp-duckduckgo-search": {
      "command": "wsl.exe",
      "args": [
        "bash",
        "-c",
        "source ~/.nvm/nvm.sh && SERPAPI_KEY=your-serpapi-api-key /home/username/.nvm/versions/node/v20.12.1/bin/npx mcp-duckduckgo-search"
      ]
    }
  }
}

Environment Variables

The server requires the following environment variable:

• SERPAPI_KEY: Your SerpAPI key (required)

API

The server implements a single MCP tool with configurable parameters:

ddg_search

Perform web searches using the DuckDuckGo search engine.

Parameters:

• query (string, required): Search query
• region (string, optional): Region code (e.g., us-en, uk-en)
  (default: us-en)
• safe_search (string, optional): Safe search level (off, moderate,
  strict) (default: moderate)
• date_filter (string, optional): Filter results by date:
  • ‘d’: past day
  • ‘w’: past week
  • ‘m’: past month
  • ‘y’: past year
  • Custom range: ‘2023-01-01…2023-12-31’
• start (number, optional): Result offset for pagination
• no_cache (boolean, optional): Bypass cache for fresh results
  (default: false)

Response includes:

• Knowledge graph data when available
• Organic search results
• News articles
• Video content
• Image results
• Related searches
• Search metadata

Development

Setup

1. Clone the repository
2. Install dependencies:

pnpm install

3. Build the project:

pnpm build

4. Run in development mode:

pnpm dev

Publishing

The project uses changesets for version management. To publish:

1. Create a changeset:

pnpm changeset

2. Version the package:

pnpm changeset version

3. Publish to npm:

pnpm release

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License - see the LICENSE file for details.

Acknowledgments

• Built on the
  Model Context Protocol
• Powered by DuckDuckGo through
  SerpAPI