DuckDuckGo Search MCP Server

Enables web searches using DuckDuckGo and integrates with Model Context Protocol (MCP) for advanced result exploration.

Local serverstdioPython★ 16

What is the DuckDuckGo Search MCP Server?

Enables web searches using DuckDuckGo and integrates with Model Context Protocol (MCP) for advanced result exploration.

What you get

A Model Context Protocol (MCP) server that provides web search capabilities using DuckDuckGo. This server enables LLMs to search the web and retrieve detailed content from websites through structured data extraction.

  • Fast and reliable — . Uses DuckDuckGo's web interface with robust HTML parsing
  • LLM-friendly — . Returns structured data optimized for AI consumption
  • Content extraction — . Intelligently extracts and summarizes webpage content
  • Related searches — . Generates contextual search suggestions

Configuration and credentials

  • Python 3.10 or newer - VS Code, Cursor, Windsurf, Claude Desktop, Goose or any other MCP client

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the DuckDuckGo Search MCP Server

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

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.10 or newer - VS Code, Cursor, Windsurf, Claude Desktop, Goose or any other MCP client
VariableDescriptionRequired
MCP_PORTConfiguration value read at startup.Optional

Example prompts to try

  • “Use DuckDuckGo Search to Cursor.”
  • “Use DuckDuckGo Search to Windsurf.”
  • “Use DuckDuckGo Search to Goose.”

Frequently asked questions

It provides features like detailed search result information, related search suggestions, pagination, rich content and metadata extraction from web pages, and even basic web spidering capabilities.