🔍 bing-search-cli

双引擎(Bing + DuckDuckGo)网页搜索与正文抓取工具

既能作为 Claude Code 插件 / MCP 服务器接入 AI Agent,也能作为独立命令行工具直接使用。

无需 API Key · 无速率限制 · 代理可选

中文 · English

✨ 简介

bing-search-cli 直接解析 Bing 和 DuckDuckGo 的公开 HTML 搜索页,解码它们的跳转链接、跨引擎去重,返回干净的结构化结果。三种用法:

• 🧩 作为 Claude Code 插件 —— 一行命令安装,自动注册 MCP 工具,替代受限的内置 WebSearch;

• 🔌 作为通用 MCP 服务器 —— 接入 Cline 或任意兼容 MCP 的客户端,给 Agent 配上不受限的联网搜索能力;

• 💻 作为命令行工具 —— 在终端里直接搜索、抓取网页正文。

Related MCP server: Web Search MCP Server

🎯 特性

📦 环境要求

• Node.js >= 18(依赖全局 fetch 与 undici)

🧩 作为 Claude Code 插件安装(推荐)

最省事的方式,无需 clone、无需手动配置。在 Claude Code 中先添加本仓库为插件市场,再安装插件:

/plugin marketplace add AusertDream/bing-search-cli
/plugin install bing-search@bing-search

安装后插件会自动注册一个走 npx 拉取的 MCP 服务器,首次调用时 npx 会自动下载并缓存依赖,之后即开即用。插件提供 bing_search 与 fetch_page 两个工具,Claude 会自动调用。

🇨🇳 代理说明: 插件通过 npx 启动的子进程会继承 Claude Code 的环境变量。国内用户在启动 Claude Code 之前先设好 HTTPS_PROXY / HTTP_PROXY 即可让插件走代理(见下文代理章节)。

让插件替代内置 WebSearch

注册插件后,Claude 会同时看到内置 WebSearch 和本插件的 bing_search,并不会自动停用前者。若想强制只走本工具,在 Claude Code 的 settings 里把内置工具加入 permissions.deny:

{
  "permissions": {
    "deny": ["WebSearch"]
  }
}

🔌 手动注册为 MCP 服务器

不想走插件、或在其他 MCP 客户端里用时,可以手动注册。最干净的方式同样是 npx 远程拉取,无需 clone:

claude mcp add bing-search -- npx -y -p github:AusertDream/bing-search-cli bing-search-mcp

需要走代理时,带上环境变量:

claude mcp add bing-search -e HTTPS_PROXY=http://127.0.0.1:7890 -- npx -y -p github:AusertDream/bing-search-cli bing-search-mcp

在 Cline 等客户端的 mcp.json 里手写也可以:

{
  "mcpServers": {
    "bing-search": {
      "command": "npx",
      "args": ["-y", "-p", "github:AusertDream/bing-search-cli", "bing-search-mcp"],
      "env": {
        "HTTPS_PROXY": "http://127.0.0.1:7890",
        "HTTP_PROXY": "http://127.0.0.1:7890"
      }
    }
  }
}

💻 作为命令行工具安装

全局安装,任意目录直接用 bing-search 命令(无需 clone):

npm install -g github:AusertDream/bing-search-cli

或者一次性运行,不安装:

npx -y -p github:AusertDream/bing-search-cli bing-search search "你的查询"

命令行用法

# 搜索(默认:10 条结果、lang=en、engine=both)
bing-search search "rust async runtime comparison"

# 更多结果 + 中文 + 仅用 Bing
bing-search search "开源大模型推理框架" 15 zh-CN bing

# 抓取并提取网页正文(默认上限 8000 字符)
bing-search fetch "https://example.com/article" 5000

参数顺序:

引擎 可选 bing / duckduckgo / both,默认 both。

🛠️ 从源码安装(开发/二次开发)

git clone https://github.com/AusertDream/bing-search-cli.git
cd bing-search-cli
npm install
npm link   # 可选:把 bing-search 命令链接到全局

直接调用脚本而不全局链接:

node cli.mjs search "你的查询"

🧰 提供的工具

bing_search —— 网页搜索

fetch_page —— 抓取并提取网页正文

⚙️ 工作原理

• Bing:解析 bing.com/search 中的 li.b_algo 区块,并把 base64 编码的 ck/a?u= 跳转链接还原成真实 URL。

• DuckDuckGo:解析 html.duckduckgo.com/html/ 中的 .result 区块,解开 uddg= 跳转参数,并跳过广告结果。

• both:合并两个引擎的结果,再按 域名 + 标题 去重。

⚠️ 由于依赖搜索引擎的公开 HTML 结构,若它们改版,解析逻辑可能需要相应更新。

🌐 关于代理

代理由环境变量控制:设置 HTTPS_PROXY 或 HTTP_PROXY 即启用,不设则直连。代码中不硬编码任何代理地址。

🇨🇳 国内用户请注意:必须配置代理。 Bing 与 DuckDuckGo 在中国大陆网络环境下通常无法直接访问(DuckDuckGo 被屏蔽,Bing 国际版亦不稳定),不挂代理会连接超时、搜不到结果。请务必先设置代理再使用:

export HTTPS_PROXY=http://127.0.0.1:7890   # 改成你自己的代理地址端口
export HTTP_PROXY=http://127.0.0.1:7890

作为插件或 MCP 服务器时,在启动 Claude Code 前设好上述环境变量,或把代理写进 mcp.json 的 env 块(见上文 MCP 配置示例)。

🤝 贡献 / Contributing

欢迎 Issue 与 PR。引擎改版导致解析失效时,修复解析器的 PR 尤其受欢迎。

📄 许可证

MIT © AusertDream

🔍 bing-search-cli  (English)

🌟 Introduction

A dual-engine (Bing + DuckDuckGo) web search and page-fetch tool. It scrapes the public HTML search pages of Bing and DuckDuckGo, decodes their redirect URLs, deduplicates across engines, and returns clean structured results. Three ways to use it:

• 🧩 As a Claude Code plugin — install with one command, auto-registers the MCP tools, replaces the rate-limited built-in WebSearch;

• 🔌 As a generic MCP server — plug it into Cline or any MCP-compatible client to give your agent unrestricted web search;

• 💻 As a standalone CLI — run searches and extract page text right from your terminal.

No API keys required.

🎯 Features

📦 Requirements

• Node.js >= 18 (uses the global fetch and undici).

🧩 Install as a Claude Code plugin (recommended)

The easiest path — no clone, no manual config. Add this repo as a plugin marketplace, then install the plugin:

/plugin marketplace add AusertDream/bing-search-cli
/plugin install bing-search@bing-search

The plugin auto-registers an MCP server launched via npx. On first call, npx downloads and caches the dependencies, then it just works. The plugin exposes two tools, bing_search and fetch_page, which Claude invokes automatically.

Proxy note: The npx-launched child process inherits Claude Code's environment variables. Set HTTPS_PROXY / HTTP_PROXY before launching Claude Code to route the plugin through a proxy (see Proxy).

Make the plugin replace the built-in WebSearch

After installing, Claude sees both the built-in WebSearch and this plugin's bing_search; it does not disable the former automatically. To force everything through this tool, add the built-in to permissions.deny in your Claude Code settings:

{
  "permissions": {
    "deny": ["WebSearch"]
  }
}

🔌 Register manually as an MCP server

If you'd rather skip the plugin, or use it in another MCP client, register it by hand. The cleanest way is the same npx remote pull, no clone:

claude mcp add bing-search -- npx -y -p github:AusertDream/bing-search-cli bing-search-mcp

With a proxy:

claude mcp add bing-search -e HTTPS_PROXY=http://127.0.0.1:7890 -- npx -y -p github:AusertDream/bing-search-cli bing-search-mcp

Or hand-write it in a client's mcp.json:

{
  "mcpServers": {
    "bing-search": {
      "command": "npx",
      "args": ["-y", "-p", "github:AusertDream/bing-search-cli", "bing-search-mcp"],
      "env": {
        "HTTPS_PROXY": "http://127.0.0.1:7890",
        "HTTP_PROXY": "http://127.0.0.1:7890"
      }
    }
  }
}

💻 Install as a CLI

Install globally to use the bing-search command anywhere (no clone):

npm install -g github:AusertDream/bing-search-cli

Or run once without installing:

npx -y -p github:AusertDream/bing-search-cli bing-search search "your query"

CLI usage

# Search (defaults: 10 results, lang=en, engine=both)
bing-search search "rust async runtime comparison"

# More results, Chinese, Bing only
bing-search search "开源大模型推理框架" 15 zh-CN bing

# Fetch and extract a page's main text (default max 8000 chars)
bing-search fetch "https://example.com/article" 5000

Argument order:

engine is one of bing / duckduckgo / both (default both).

🛠️ Install from source (development)

git clone https://github.com/AusertDream/bing-search-cli.git
cd bing-search-cli
npm install
npm link   # optional: link the bing-search command globally

Call the script directly without linking:

node cli.mjs search "your query"

🧰 Exposed tools

bing_search — search the web.

fetch_page — fetch and extract readable text from a URL.

⚙️ How it works

• Bing: parses li.b_algo blocks from bing.com/search and decodes the base64 ck/a?u= redirect wrappers back to real URLs.

• DuckDuckGo: parses .result blocks from html.duckduckgo.com/html/ and unwraps the uddg= redirect params, skipping ad results.

• both: concatenates results from both engines, then deduplicates by domain + title.

⚠️ Because this relies on the engines' public HTML markup, result parsing may need updating if they change their page structure.

🌐 Proxy

Proxy is controlled entirely by environment variables. Set HTTPS_PROXY or HTTP_PROXY to enable it; leave them unset for direct connections. No proxy address is hardcoded.

🇨🇳 Users in mainland China: a proxy is required. Bing and DuckDuckGo are generally not reachable from within mainland China (DuckDuckGo is blocked, and international Bing is unstable), so without a proxy you'll hit connection timeouts and get no results. Set a proxy first:

export HTTPS_PROXY=http://127.0.0.1:7890   # replace with your own proxy host:port
export HTTP_PROXY=http://127.0.0.1:7890

When running as a plugin or MCP server, set these before launching Claude Code, or put the proxy in the env block of mcp.json (see the MCP config example above).

🤝 Contributing

Issues and PRs welcome — especially parser fixes when an engine changes its markup.

📄 License

MIT © AusertDream