DuckDuckGo & Felo AI Search
搜索与获取by OEvortex
提供快速、重隐私的 Web 与 AI 搜索,集成内容和元数据提取,支持无 API keys 抓取、缓存、限流与 user agent 安全配置。
什么是 DuckDuckGo & Felo AI Search?
提供快速、重隐私的 Web 与 AI 搜索,集成内容和元数据提取,支持无 API keys 抓取、缓存、限流与 user agent 安全配置。
README
[!IMPORTANT] DuckDuckGo Search MCP supports the Model Context Protocol (MCP) standard, making it compatible with various AI assistants and tools.
✨ Features
<div style="display: flex; flex-wrap: wrap; gap: 1.5em; margin-bottom: 1.5em;"> <div><b>🌐 Web search</b> using DuckDuckGo HTML</div> <div><b>🧠 AI search</b> using IAsk AI, Monica & Brave AI</div> <div><b>⚡ Performance optimized</b> with caching</div> <div><b>🛡️ Security features</b> including rate limiting and rotating user agents</div> <div><b>🔌 MCP-compliant</b> server implementation</div> <div><b>🆓 No API keys required</b> - works out of the box</div> </div>[!IMPORTANT] Unlike many search tools, this package performs actual web scraping rather than using limited APIs, giving you more comprehensive results.
🚀 Quick Start
<div style="background: #222; color: #fff; padding: 1.5em; border-radius: 8px; margin: 1.5em 0;"> <b>Run instantly with npx:</b>npx -y @oevortex/ddg_search@latest
[!TIP] This will download and run the latest version of the MCP server directly without installation – perfect for quick use with AI assistants.
🛠️ Installation Options
<details> <summary><b>Global Installation (npm)</b></summary>npm install -g @oevortex/ddg_search
Run globally:
ddg-search-mcp
yarn global add @oevortex/ddg_search
Run globally:
ddg-search-mcp
pnpm add -g @oevortex/ddg_search
Run globally:
ddg-search-mcp
git clone https://github.com/OEvortex/ddg_search.git
cd ddg_search
npm install
npm start
Or with Yarn:
yarn install
yarn start
Or with pnpm:
pnpm install
pnpm start
🧑💻 Command Line Options
npx -y @oevortex/ddg_search@latest --help
[!TIP] Use the <code>--version</code> flag to check which version you're running.
🤖 Using with MCP Clients
[!IMPORTANT] The most common way to use this tool is by integrating it with MCP-compatible AI assistants.
Add the server to your MCP client configuration:
{
"mcpServers": {
"ddg-search": {
"command": "npx",
"args": ["-y", "@oevortex/ddg_search@latest"]
}
}
}
Or if installed globally:
{
"mcpServers": {
"ddg-search": {
"command": "ddg-search-mcp"
}
}
}
[!TIP] After configuring, restart your MCP client to apply the changes.
🧰 Tools Overview
<div style="display: flex; flex-wrap: wrap; gap: 2.5em; margin: 1.5em 0;"> <div style="margin-bottom: 1.5em;"> <b>🔍 Web Search Tool</b><br/> <code>web-search</code><br/> <ul> <li><b>query</b> (string, required): The search query</li> <li><b>page</b> (integer, optional, default: 1): Page number</li> <li><b>numResults</b> (integer, optional, default: 10): Number of results (1-20)</li> </ul> <i>Example: Search the web for "climate change solutions"</i> </div> <div style="margin-bottom: 1.5em;"> <b>🧠 IAsk AI Search Tool</b><br/> <code>iask-search</code><br/> <ul> <li><b>query</b> (string, required): The search query or question</li> <li><b>mode</b> (string, optional, default: "question"): Search mode - "question", "academic", "forums", "wiki", or "thinking"</li> <li><b>detailLevel</b> (string, optional): Response detail level - "concise", "detailed", or "comprehensive"</li> </ul> <i>Example: Search IAsk AI for "Explain quantum computing in simple terms"</i> </div> <div style="margin-bottom: 1.5em;"> <b>🤖 Monica AI Search Tool</b><br/> <code>monica-search</code><br/> <ul> <li><b>query</b> (string, required): The search query or question</li> </ul> <i>Example: Search Monica AI for "Latest advancements in AI"</i> </div> </div>📁 Project Structure
bin/ # Command-line interface
src/
index.js # Main entry point
tools/ # Tool definitions and handlers
searchTool.js
iaskTool.js
monicaTool.js
utils/
search.js # Search and URL utilities
user_agents.js
search_monica.js
search_iask.js # IAsk AI search utilities
package.json
README.md
🤝 Contributing
Contributions are welcome! Please open issues or submit pull requests.
[!NOTE] Please follow the existing code style and add tests for new features.
📺 YouTube Channel
<div align="center"> <a href="https://youtube.com/@OEvortex"><img src="https://img.shields.io/badge/YouTube-%40OEvortex-red.svg" alt="YouTube Channel" /></a> <br/> <a href="https://youtube.com/@OEvortex">youtube.com/@OEvortex</a> </div>📄 License
Apache License 2.0
[!NOTE] This project is licensed under the Apache License 2.0 – see the <a href="LICENSE">LICENSE</a> file for details.
<div align="center"> <sub>Made with ❤️ by <a href="https://youtube.com/@OEvortex">@OEvortex</a></sub> </div>
常见问题
DuckDuckGo & Felo AI Search 是什么?
提供快速、重隐私的 Web 与 AI 搜索,集成内容和元数据提取,支持无 API keys 抓取、缓存、限流与 user agent 安全配置。
相关 MCP Server
网页抓取
编辑精选by Anthropic
Fetch 是 MCP 官方参考服务器,让 AI 能抓取网页并转为 Markdown 格式。
✎ 这个服务器解决了 AI 直接处理网页内容时格式混乱的问题,适合需要让 Claude 分析在线文档或新闻的开发者。不过作为参考实现,它缺乏生产级的安全配置,你得自己处理反爬虫和隐私风险。
Puppeteer 浏览器控制
编辑精选by Anthropic
Puppeteer 是让 Claude 自动操作浏览器进行网页抓取和测试的 MCP 服务器。
✎ 这个服务器解决了手动编写 Puppeteer 脚本的繁琐问题,适合需要自动化网页交互的开发者,比如抓取动态内容或做端到端测试。不过,作为参考实现,它可能缺少生产级的安全防护,建议在可控环境中使用。
Brave 搜索
编辑精选by Anthropic
Brave Search 是让 Claude 直接调用 Brave 搜索 API 获取实时网络信息的 MCP 服务器。
✎ 如果你想让 AI 助手帮你搜索最新资讯或技术文档,这个工具能绕过传统搜索的限制,直接返回结构化数据。特别适合需要实时信息的开发者,比如查 API 更新或竞品动态。不过它依赖 Brave 的 API 配额,高频使用可能受限。