mcpField
M
Mcp Web Scraper

Mcp Web Scraper

Local
github.com/asdqwsadqBrowser Automation0Updated 24w ago

About Mcp Web Scraper

Mcp Web Scraper is an MCP server for extracting readable webpage text, producing AI summaries, and searching the web. It is suited to MCP clients that need page content and search results through a small set of tools.

Key features

  1. 01Extract readable text from webpages
  2. 02Generate multilingual AI summaries
  3. 03Search the web with Tavily

Use cases

  1. 01Retrieve an article without page clutter
  2. 02Summarize a webpage in another language
  3. 03Find web results for an Agent

MCP support

Exposes fetch_url, summarize_url, and search_web tools to MCP clients over HTTP. The server uses NVIDIA NIM for summaries and Tavily Search for web search.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Web Scraper + AI Summarizer

🕸️ 网页抓取与AI智能摘要工具 — 一个 MCP (Model Context Protocol) 工具,抓取任何网页内容并用 AI 生成智能摘要

Smithery MCP.so License

📋 功能

工具描述
🔧 fetch_url抓取指定 URL 的网页内容,自动提取可读文本(移除导航、脚本、广告等干扰元素)
🤖 summarize_url抓取网页内容并用 AI 生成智能摘要(支持多语言:中文、English、日本語等)
🔍 search_web通过搜索引擎搜索网络信息(基于 Tavily Search API,专为 AI Agent 优化)

🚀 快速开始

方式一:通过 Smithery 使用(推荐)

直接在支持 MCP 的客户端(如 Cursor、Claude Desktop)中搜索 web-scraper-ai-summarizer 安装即可。

方式二:自托管部署
# 1. 克隆仓库
git clone https://github.com/asdqwsadq/mcp-web-scraper.git
cd mcp-web-scraper

# 2. 配置环境变量
cp .env.example .env
# 编辑 .env 填入你的 API Key
# - NVIDIA_API_KEY: AI摘要(免费,注册 https://build.nvidia.com)
# - TAVILY_API_KEY: 网络搜索(免费,注册 https://tavily.com)

# 3. 安装依赖
pip install -r requirements.txt

# 4. 启动服务
python3 -m uvicorn server:app --host 0.0.0.0 --port 8080
方式三:Docker 部署
docker build -t mcp-web-scraper .
docker run -d --name mcp-web-scraper -p 8080:8080 --env-file .env mcp-web-scraper

🔧 MCP 协议调用示例

1. 抓取网页
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "fetch_url",
    "arguments": {
      "url": "https://example.com/article",
      "max_size": 30000
    }
  }
}
2. AI 摘要
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "summarize_url",
    "arguments": {
      "url": "https://example.com/article",
      "language": "中文"
    }
  }
}
3. 网络搜索
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search_web",
    "arguments": {
      "query": "最新人工智能技术趋势",
      "count": 5
    }
  }
}

🔑 API 密钥配置

服务用途免费额度申请地址
🧠 NVIDIA NIMAI 摘要生成1000 credits(无需信用卡)https://build.nvidia.com
🔍 Tavily Search网络搜索1000 次/月https://tavily.com
🔐 XPack(可选)用户认证 & 计费自部署见 XPack 文档

📦 技术架构

┌─────────────┐     HTTP/MCP      ┌──────────────────┐
│   MCP 客户端  │ ◄─────────────►  │  MCP HTTP Server  │
│ (Cursor/Cline)│                  │  (FastAPI + MCP)  │
└─────────────┘                    └────────┬─────────┘
                                            │
                    ┌───────────────────────┼───────────────────┐
                    │                       │                   │
                    ▼                       ▼                   ▼
            ┌──────────────┐     ┌──────────────┐     ┌──────────────┐
            │  NVIDIA NIM  │     │ Tavily Search│     │  XPack Auth  │
            │  (AI摘要)     │     │  (网络搜索)   │     │  (计费)       │
            └──────────────┘     └──────────────┘     └──────────────┘

🛠️ 开发

# 启动开发服务器(热重载)
uvicorn server:app --host 0.0.0.0 --port 8080 --reload

# MCP 协议测试
curl -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

📄 协议

MIT License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.