mcp-web-search
Provides web search and page fetching capabilities via Serper.dev or DuckDuckGo, deployable on Render with SSE transport.
README
MCP Web Search Server
A Model Context Protocol (MCP) server that provides web search capabilities, deployable on Render.
Built with Python using the official MCP SDK, supporting SSE (Server-Sent Events) and Streamable HTTP transports for AIPI.
Tools exposed
| Tool | Description |
|---|---|
web_search |
Search the web. Returns titles, URLs, and descriptions. |
fetch_page |
Fetch and extract text content from any URL. |
🚀 Deploy to Render (step-by-step)
1. Push this repo to GitHub
cd mcp-web-search
git init
git add .
git commit -m "Initial commit"
# create a repo on github.com, then:
git remote add origin https://github.com/YOUR_USERNAME/mcp-web-search.git
git push -u origin main
2. Create a new Web Service on Render
- Go to render.com → New → Web Service
- Connect your GitHub repo (
mcp-web-search) - Render will auto-detect
render.yaml— click Apply - Set environment variables in the Render dashboard:
| Variable | Required | Description |
|---|---|---|
SERPER_API_KEY |
Recommended | Get free at serper.dev — 2,500 queries/month free (Google results) |
MCP_API_KEY |
Optional | Set to any secret string to password-protect your server |
- Click Create Web Service — Render will build and deploy automatically.
Your server URL will be: https://mcp-web-search.onrender.com (or similar)
🔌 Connect to AIPI
In AIPI's Add Custom MCP screen, use this flat configuration (no wrapper object):
SSE:
{
"url": "https://mcp-web-search-j73g.onrender.com/sse",
"name": "web-search",
"type": "sse"
}
Streamable HTTP:
{
"url": "https://mcp-web-search-j73g.onrender.com/mcp",
"name": "web-search",
"type": "streamable"
}
Replace the host with your actual Render service URL if different. AIPI uses a flat
url / name / type object — it does not use a mcpServers wrapper.
🔍 Search Providers
| Provider | Key required | Quality | Limit |
|---|---|---|---|
| Serper.dev | Yes (free) | ⭐⭐⭐⭐⭐ | 2,500 queries/month free (Google results) |
| DuckDuckGo | No | ⭐⭐⭐ | Unlimited (fallback) |
Set SERPER_API_KEY in Render env vars to use Serper. The server falls back to DuckDuckGo automatically if the key is absent.
🧪 Test locally
pip install -r requirements.txt
SERPER_API_KEY=your_key python server.py
Health check:
curl http://localhost:3000/
The server runs on port 3000 by default. Set PORT environment variable to change it.
⚠️ Free tier note
Render's free tier spins down after 15 minutes of inactivity (cold start ~30s). Upgrade to the Starter plan ($7/mo) to keep it always-on.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。