npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

mcp_hsx_ai_search

v1.4.13

Published

HSX AI Search MCP Server - 网页自动化调用豆包/DeepSeek,使用你自己账号的免费额度

Readme

mcp_hsx_ai_search

HSX AI Search MCP Server - 网页自动化调用豆包/DeepSeek,使用你自己账号的免费额度。

功能

通过 Claude Code MCP 直接调用 你自己已登录 的豆包/DeepSeek网页版进行问答,直接获取AI处理后的答案,节省token,效果更好。

核心思路

原来搜索MCP模式:本地 Claude → 搜索网页 → 本地 Claude 处理 → 浪费大量token,效果差

本MCP模式:本地 Claude → 你的豆包/DeepSeek账号 → AI处理 → 本地直接得到答案 → AI已经处理好,直接拿结果

安装

第一步:在 Claude Code 添加 MCP

Windows (PowerShell):

claude mcp add-json mcp_hsx_ai_search -s user '{"command": "cmd", "args":["/c", "npx", "-y", "mcp_hsx_ai_search@latest"]}'

macOS / Linux:

claude mcp add mcp_hsx_ai_search -- npx -y mcp_hsx_ai_search@latest

手动配置(也可以直接编辑 ~/.mcp.json)

Windows:

{
  "mcpServers": {
    "mcp_hsx_ai_search": {
      "command": "cmd",
      "args": [
        "/c",
        "npx",
        "-y",
        "mcp_hsx_ai_search@latest"
      ]
    }
  }
}

macOS / Linux:

{
  "mcpServers": {
    "mcp_hsx_ai_search": {
      "command": "npx",
      "args": [
        "-y",
        "mcp_hsx_ai_search@latest"
      ]
    }
  }
}

第二步:登录你的账号

第一次用会报错,别慌。运行 setup:

登录 DeepSeek:

npx -p mcp_hsx_ai_search mcp_hsx_ai_search-setup deepseek

登录 豆包:

npx -p mcp_hsx_ai_search mcp_hsx_ai_search-setup doubao

会弹个浏览器窗口出来,打开对应的网站,登录你的账号就行。有验证码就过一下,登录完成后关掉浏览器,登录状态会自动保存。

之后就不用管了,cookie会保存,下次直接用。

使用方法

在 Claude Code 中:

用hsx ai搜索一下 xxx

或者手动调用:

{
  "name": "ai_search",
  "arguments": {
    "query": "2026年3月最新新闻",
    "provider": "deepseek"
  }
}

参数说明:

  • query: 搜索查询问题(必填)
  • provider: AI平台,deepseekdoubao,默认 deepseek
  • browser: 浏览器选择,edge/chrome/auto,默认 auto(自动检测,优先Edge)
  • headless: 是否无头模式,默认 false(显示浏览器)

静默模式(不弹窗浏览器)

如果你已经登录完成,想要每次搜索不弹出浏览器窗口,可以通过环境变量设置默认无头模式:

Windows (修改 MCP 配置):

{
  "mcpServers": {
    "mcp_hsx_ai_search": {
      "command": "cmd",
      "args": ["/c", "set MCP_HSX_HEADLESS=true && npx", "-y", "mcp_hsx_ai_search@latest"]
    }
  }
}

macOS / Linux (修改 MCP 配置):

{
  "mcpServers": {
    "mcp_hsx_ai_search": {
      "command": "env",
      "args": ["MCP_HSX_HEADLESS=true", "npx", "-y", "mcp_hsx_ai_search@latest"]
    }
  }
}

设置后,每次搜索都不会弹出浏览器窗口,后台静默运行完成搜索。

如何重新登录

如果登录失效了,重新跑一遍 setup 就行了:

npx -p mcp_hsx_ai_search mcp_hsx_ai_search-setup [deepseek|doubao]

特点

  • ✅ 使用你自己的账号,免费额度够用
  • ✅ 不需要申请API Key,直接浏览器登录就行
  • ✅ 支持 DeepSeek 网页版 和 豆包网页版
  • ✅ 支持 Edge 浏览器Chrome 浏览器,自动检测优先Edge
  • ✅ 和 huge-ai-search 同一个思路,但是支持国内AI

工作原理

本地 Claude → mcp_hsx_ai_search → Puppeteer 打开浏览器 → 读取已保存cookie → 发送问题 → 等待回答 → 返回答案给 Claude

许可证

MIT