DuckDuckGo MCP Server

Name: DuckDuckGo MCP Server
Author: rsimd

@rsimd

リポジトリ

DuckDuckGo MCP Server について

DuckDuckGo MCP Server for Claude Desktop and Cursor

#duckduckgo #mcp-server #search-engine

基本情報

カテゴリ

検索

ランタイム

python

トランスポート

stdio

公開者

rsimd

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "duckduckgo-mcp-server-rsimd": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is DuckDuckGo MCP Server?

DuckDuckGo MCP Server is a Model Context Protocol (MCP) server that provides web search functionality using DuckDuckGo. It is designed for use with MCP-compatible applications such as Claude Desktop and Cursor IDE.

How to use DuckDuckGo MCP Server?

Install dependencies using uv sync (recommended) or pip install -r requirements.txt. Start the server with uv run duckduckgo-mcp-server or python run.py. Configure your MCP client (e.g., Claude Desktop or Cursor) to use the server by specifying the command and arguments in the client's MCP settings JSON. The server exposes a single tool: search_duckduckgo.

Key features of DuckDuckGo MCP Server

Web page search via DuckDuckGo
Summarization and detailed info retrieval from search results
Asynchronous processing for fast searches
Fallback mechanism for stability
No special configuration required

Use cases of DuckDuckGo MCP Server

Provide real-time web search capabilities to AI assistants
Enable code editors like Cursor to fetch current information
Support MCP clients for automated information retrieval
Run searches in Dockerized environments

FAQ from DuckDuckGo MCP Server

What MCP clients are supported?

Claude Desktop (Mac/Windows/Linux), Cursor IDE, and any other MCP-compatible application.

What are the prerequisites?

Python 3.11 or later (Python 3.13 recommended) and the uv package manager (recommended) or pip.

How do I configure the server in my client?

Set the MCP server command to uv run duckduckgo-mcp-server (when using uv) or python server.py (with pip), with the appropriate working directory and environment.