Agenten stärken
Installation vom Herausgeber. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
Noch kein paketiertes Release in der Registry. Folgen Sie der README des Repositorys.
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
StartenVom Herausgeber
MCP server with web search (Serper) and page scraping (ScrapingDog) tools for AI assistants - runs on Cloudflare Workers
| 🌐 Web Search | Search the web using Google via Serper API |
| 📄 Page Scraping | Extract content from any webpage using ScrapingDog |
| ⚡ Edge Deployment | Runs on Cloudflare Workers for ultra-low latency |
| 🔌 MCP Compatible | Works with Claude, Kiro, and any MCP client |
| 🔒 Secure | API keys stored as encrypted secrets |
web_searchSearch the web using Google via Serper API.
{
"query": "latest AI news",
"num_results": 10,
"search_type": "search"
}
scrape_pageExtract content from a web page.
{
"url": "https://example.com",
"render_js": true,
"premium": false
}
📦 Web-search-MCP
├── 📂 src/
│ ├── 📄 index.ts # 🚀 Main entry & router
│ ├── 📂 clients/
│ │ ├── 📄 serper.ts # 🔍 Serper API client
│ │ └── 📄 scrapingdog.ts # 🐕 ScrapingDog client
│ ├── 📂 handlers/
│ │ ├── 📄 mcp.ts # 📡 MCP JSON-RPC handler
│ │ └── 📄 sse.ts # 📺 SSE session handler
│ ├── 📂 tools/
│ │ ├── 📄 registry.ts # 📋 Tool registry
│ │ ├── 📄 web-search.ts # 🔎 Search tool
│ │ └── 📄 scrape-page.ts # 📄 Scrape tool
│ └── 📂 validators/
│ └── 📄 index.ts # ✅ Input validators
├── 📄 wrangler.toml # ⚙️ Cloudflare config
├── 📄 package.json
├── 📄 tsconfig.json
└── 📄 vitest.config.ts
Before you begin, ensure you have:
git clone https://github.com/pritthwishGC/Web-search-MCP.git
cd Web-search-MCP
npm install
Create a .dev.vars file:
SERPER_API_KEY=your_serper_api_key_here
SCRAPINGDOG_API_KEY=your_scrapingdog_api_key_here
npm run dev
🎉 Server running at http://localhost:8787
npx wrangler login
npx wrangler secret put SERPER_API_KEY
# 📝 Enter your Serper API key when prompted
npx wrangler secret put SCRAPINGDOG_API_KEY
# 📝 Enter your ScrapingDog API key when prompted
npm run deploy
✅ Your MCP server is now live at:
https://web-search-mcp-server.<your-subdomain>.workers.dev
# 🔄 Update Serper API key
npx wrangler secret put SERPER_API_KEY
# 🔄 Update ScrapingDog API key
npx wrangler secret put SCRAPINGDOG_API_KEY
💡 No redeployment needed! Secrets update immediately.
Add this to your MCP client config:
{
"mcpServers": {
"web-search": {
"url": "https://web-search-mcp-server.<your-subdomain>.workers.dev/mcp"
}
}
}
# Run tests once
npm test
# Run tests in watch mode
npm run test:watch
MIT © pritthwishGC
MCP server with web search (Serper) and page scraping (ScrapingDog) tools for AI assistants - runs on Cloudflare Workers
Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Web Search läuft lokal über stdio.
Zuletzt geprüft: 2026-10-27. MCP server with web search (Serper) and page scraping (ScrapingDog) tools for AI assistants - runs on Cloudflare Workers