DuckDuckGo Search MCP server

This MCP server provides web search functionality through DuckDuckGo, allowing AI assistants to retrieve up-to-date information from the internet. It offers customizable search parameters and returns structured results with useful metadata.

Installation

Via Smithery

The easiest way to install and connect the DuckDuckGo search capability to Claude is through Smithery:

npx -y @smithery/cli install duck-duck-mcp --client claude

You can also run it directly without installation:

npx -y @smithery/cli install duck-duck-mcp --client claude

Usage

Starting the Server

# Using npx (recommended)
npx duck-duck-mcp

# Or if globally installed
mcp-server-search

Search Parameters

The server accepts the following parameters in your search requests:

{
  "query": "your search keywords",
  "options": {
    "region": "zh-cn",
    "safeSearch": "MODERATE",
    "numResults": 50
  }
}

Customization Options

• region: Sets the regional context for search results (default: zh-cn)
• safeSearch: Controls the filtering level with three options:
  • OFF: No content filtering
  • MODERATE: Some filtering (default)
  • STRICT: Maximum content filtering
• numResults: Number of search results to return (default: 50)

Response Format

The server returns search results in this structured format:

{
  "type": "search_results",
  "data": [
    {
      "title": "Result title",
      "url": "Result URL",
      "description": "Result description",
      "metadata": {
        "type": "article|documentation|social|other",
        "source": "domain name"
      }
    }
  ],
  "metadata": {
    "query": "search query",
    "timestamp": "timestamp",
    "resultCount": 50,
    "searchContext": {
      "region": "zh-cn",
      "safeSearch": "MODERATE"
    },
    "queryAnalysis": {
      "language": "zh-cn|en",
      "topics": ["technology", "documentation"]
    }
  }
}

Result Metadata

The server automatically enhances results with:

• Content type classification (article, documentation, social media, etc.)
• Source domain information
• Language detection
• Topic tag identification

This metadata helps AI assistants better understand and contextualize the search results when providing information to users.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.