Back to MCP Catalog

DuckDuckGo Search MCP Server

SearchTypeScript
Perform web searches using DuckDuckGo's search engine
Available Tools

duckduckgo_search

Perform web searches using DuckDuckGo API. Returns formatted Markdown search results.

querycountsafeSearch

DuckDuckGo Search provides a simple and efficient way to perform web searches directly through the DuckDuckGo search engine. This MCP server enables AI assistants to retrieve up-to-date information from the web, enhancing their ability to provide relevant and current information to users. The server includes features like customizable search parameters, rate limiting to prevent abuse, and formatted Markdown results for easy readability. It's built with TypeScript and follows the Model Context Protocol standards for seamless integration with compatible AI assistants.

Overview

DuckDuckGo Search MCP allows AI assistants to perform web searches using the DuckDuckGo search engine. This enables access to up-to-date information from the internet, helping to provide more accurate and current responses.

Installation

Using NPM (Recommended)

The easiest way to install the DuckDuckGo Search MCP is through NPM:

npm install -g duckduckgo-mcp-server

Manual Installation

If you prefer to install from source:

  1. Clone the repository:

    git clone https://github.com/zhsama/duckduckgo-mcp-server.git
    cd duckduckgo-mcp-server
    
  2. Install dependencies:

    npm install -g pnpm
    pnpm install
    
  3. Build the server:

    pnpm run build
    

Configuration

Claude Desktop Configuration

To use this MCP with Claude Desktop, add the following to your configuration file:

On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

For the NPM installation:

{
  "mcpServers": {
    "duckduckgo-search": {
      "command": "npx",
      "args": [
        "-y",
        "duckduckgo-mcp-server"
      ]
    }
  }
}

For local installation:

{
  "mcpServers": {
    "duckduckgo-search": {
      "command": "node",
      "args": [
        "/path/to/duckduckgo-search/build/index.js"
      ]
    }
  }
}

Rate Limits

The server has the following rate limits:

  • Maximum 1 request per second
  • Maximum 15,000 requests per month

Usage

Once installed and configured, you can use the DuckDuckGo search functionality by asking the AI assistant to search for information. For example:

  • "Search for the latest news about renewable energy"
  • "Find information about the history of Rome"
  • "Look up recipes for vegetarian pasta dishes"

The search results will be returned in a formatted Markdown format for easy readability.

Debugging

If you encounter issues with the MCP server, you can use the MCP Inspector for debugging:

pnpm run inspector

This will provide a URL to access debugging tools in your browser, which can help identify communication issues between the AI assistant and the MCP server.

Related MCPs

SearXNG
SearchTypeScript

Web search capabilities through SearXNG API integration

Hacker News
SearchPython

Access and search Hacker News content programmatically

Web Search
SearchJavaScript

Free Google search integration with no API keys required

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.