DuckDuckGo

A DuckDuckGo search plugin for Model Context Protocol (MCP), compatible with Claude Code. Provides web search functionality with advanced navigation and content exploration features.

python

11

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "gianlucamazza-mcp-duckduckgo": {
      "command": "mcp-duckduckgo",
      "args": [],
      "env": {
        "MCP_PORT": "Set the port for the server (default 3000)"
      }
    }
  }
}

You can use the MCP DuckDuckGo server to perform web searches and retrieve structured, AI-friendly results from DuckDuckGo. It’s designed to be fast, parsing search results and extracting webpage content for easy consumption by your language model or copilots.

How to use

Start the DuckDuckGo MCP server and connect it to your MCP client. You can perform a web search, fetch page content, or request related search suggestions. Use the server as a scalable web search backend that returns structured data optimized for AI consumption.

How to install

Prerequisites: Python 3.10 or newer. You may also want a development environment such as VS Code or any MCP client you use (Cursor, Windsurf, Claude Desktop, Goose, LM Studio, or another). Install Python dependencies and the MCP server binary as described.

Install from source using the standard MCP server configuration shown in the code example.

{
  "mcpServers": {
    "duckduckgo-search": {
      "command": "mcp-duckduckgo"
    }
  }
}

Configuration

DuckDuckGo MCP server supports the following arguments and environment variables.

mcp-duckduckgo --help

Environment variables

Set the port that the server listens on. The default port is 3000.

export MCP_PORT=8080

Available operations

Web search: queries the web using DuckDuckGo and returns a list of results with structured data.

Get page content: fetches and extracts content from a specific URL.

Suggest related searches: generates contextual search suggestions for a given query.

Notes and tips

If you plan to use multiple MCP clients or automation, standardize on the duckduckgo-search MCP server name and its mcp-duckduckgo command to ensure compatibility across tools.

Available tools

web_search

Search the web using DuckDuckGo and return structured results suitable for AI consumption.

get_page_content

Fetch a URL and extract structured content from the page for downstream processing.

suggest_related_searches

Generate contextual search suggestions based on the original query to help refine exploration.