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. |
๐ 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 โ New โ Web Service
- Connect your GitHub repo (
mcp-web-search) - Render will auto-detect
render.yamlโ click Apply - Set environment variables in the Render dashboard:
| Variable | Required | Description |
|---|---|---|
SERPER_API_KEY |
Recommended | Get free at serper.dev โ 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 โ Render will build and deploy automatically.
Your server URL will be: https://mcp-web-search.onrender.com (or similar)
๐ 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 โ it does not use a mcpServers wrapper.
๐ Search Providers
| Provider | Key required | Quality | Limit |
|---|---|---|---|
| Serper.dev | Yes (free) | โญโญโญโญโญ | 2,500 queries/month free (Google results) |
| DuckDuckGo | No | โญโญโญ | 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.
๐งช 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.
โ ๏ธ 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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.