mcp-web-search
MCP Web Search
一个使用 DuckDuckGo 进行网络搜索的模型上下文协议(MCP)服务器。无需 API 密钥。
功能特性
网络搜索 - 通过 DuckDuckGo 的静态 HTML 界面进行网络搜索
内容提取 - 使用 Mozilla 的 Readability 从任意网页获取并提取可读内容
零配置 - 无需 API 密钥,无需注册,开箱即用
轻量级 - 使用 Node.js 原生
fetch,无需重型浏览器自动化
Related MCP server: Web Scout MCP Server
工具
工具 | 描述 |
| 使用 DuckDuckGo 搜索网络。返回每条结果的标题、URL 和摘要。 |
| 从网页 URL 提取主要文本内容。去除广告、导航和噪音。 |
使用方法
本地安装
git clone https://github.com/doranobik/mcp-web-search.git
cd mcp-web-search
npm install
npm run build
node dist/index.js注意: 此包未发布到 npm。npm 上的
mcp-web-search名称属于一个无关项目,请从本仓库安装。
Docker
docker build -t mcp-web-search .
docker run -i mcp-web-searchMCP 客户端配置
Claude Desktop(claude_desktop_config.json):
{
"mcpServers": {
"web-search": {
"command": "node",
"args": ["/path/to/mcp-web-search/dist/index.js"]
}
}
}LM Studio(mcp.json):
{
"mcpServers": {
"web-search": {
"command": "node",
"args": ["/path/to/mcp-web-search/dist/index.js"]
}
}
}工具参数
webSearch
参数 | 类型 | 必填 | 默认值 | 描述 |
| string | 是 | - | 搜索查询 |
| number | 否 | 10 | 最大结果数(1-20) |
| string | 否 | - | 区域代码(例如 |
fetchWebContent
参数 | 类型 | 必填 | 默认值 | 描述 |
| string | 是 | - | 要获取的 URL |
| number | 否 | 5000 | 返回的最大字符数(100-200000) |
免责声明
此服务器通过解析 DuckDuckGo 的 HTML 界面(而非官方 API)来搜索网络。如果 DuckDuckGo 更改其标记,它可能会失效,并且大量自动化使用可能违反 DuckDuckGo 的服务条款或导致速率限制。请负责任地使用,风险自负。
许可证
MIT — 详情请参阅 LICENSE。
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables web searching through DuckDuckGo and fetching content from webpages. Provides search capabilities with configurable result limits and webpage content extraction for AI assistants.
- AlicenseBqualityAmaintenanceEnables privacy-focused web searches using DuckDuckGo and extraction of clean, readable content from web pages with support for parallel processing of multiple URLs.282132Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables web search and content fetching via DuckDuckGo without requiring an API key.843MIT
- AlicenseNot gradedqualityCmaintenanceEnables web search using Bing and DuckDuckGo combined, and fetching readable content from web pages, with no API key required.91MIT
Related MCP Connectors
Search the web and extract clean, readable text from webpages. Process multiple URLs at once to sp…
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Read any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/doranobik/mcp-web-search'
If you have feedback or need assistance with the MCP directory API, please join our Discord server