Web Intelligence MCP Server
Provides AI agents with real-time web capabilities including live search results, markdown web scraping, business lead generation, and detailed company information. It enables agents to bypass knowledge cutoffs by accessing current web data through a monetized Apify Actor.
README
Web Intelligence MCP Server
Real-time web intelligence for AI agents. Monetized on Apify.
What This Does
A production-ready MCP server that gives AI agents real-time web capabilities:
| Tool | What It Does | Price |
|---|---|---|
search_web |
Live Google/Bing search results | $0.02/call |
scrape_page |
Clean markdown from any URL | $0.05/call |
find_leads |
Google Maps business data | $0.10/call |
get_company_info |
Tech stack, employees, contacts | $0.15/call |
Why Agents Need This:
- Claude/GPT have knowledge cutoffs
- Agents need current prices, news, company info
- Every serious agent workflow needs real-time data
Quick Start
For AI Agents (Claude, Cursor, etc.)
Add to your MCP config:
{
"mcpServers": {
"web-intelligence": {
"url": "https://your-username--web-intelligence-mcp.apify.actor/sse"
}
}
}
For Developers (Publish Your Own)
# 1. Clone and setup
git clone <your-repo>
cd web-intelligence-mcp
npm install
# 2. Configure API keys
cp .env.example .env
# Edit .env with your keys
# 3. Test locally
npm run build
apify run
# 4. Deploy to Apify
apify login
apify push
API Keys Required
| Service | Purpose | Get Key At |
|---|---|---|
| SerpAPI | Web search | serpapi.com |
| Jina AI | Web scraping | jina.ai/reader |
| Google Places | Lead generation | Google Cloud |
| Clearbit | Company data | clearbit.com |
Free tiers available for all!
Tool Examples
search_web
{
"query": "AI agent startups funding 2024",
"num_results": 10
}
scrape_page
{
"url": "https://example.com/article"
}
find_leads
{
"keyword": "software companies",
"location": "San Francisco, CA",
"max_results": 20
}
get_company_info
{
"domain": "stripe.com"
}
Monetization
This Actor uses Apify Pay-Per-Event:
| Event | Price | When Charged |
|---|---|---|
search-web |
$0.02 | Every search_web call |
scrape-page |
$0.05 | Every scrape_page call |
find-leads |
$0.10 | Every find_leads call |
company-info |
$0.15 | Every get_company_info call |
Your earnings: 80% of revenue (Apify takes 20% commission)
Deployment
Option 1: Apify Console (Easiest)
- Go to Apify Console
- Create new Actor from GitHub repo
- Set environment variables
- Enable "Standby mode" in settings
- Set pricing in "Monetization" tab
Option 2: CLI
# Install Apify CLI
npm install -g apify-cli
# Login
apify login
# Push to Apify
apify push
# Set secrets
apify secrets:set SERPAPI_KEY your_key_here
apify secrets:set JINA_AI_KEY your_key_here
# ... etc
Standby Mode
Standby mode gives you a persistent URL that MCP clients can connect to:
https://your-username--web-intelligence-mcp.apify.actor/sse
This URL stays active even when the Actor isn't running. Apify automatically starts it when a request comes in.
Configuration
Environment Variables
Create .env file:
# Required
SERPAPI_KEY=your_serpapi_key
JINA_AI_KEY=your_jina_key
GOOGLE_PLACES_API_KEY=your_google_key
CLEARBIT_API_KEY=your_clearbit_key
# Optional
APIFY_LOG_LEVEL=INFO
Pricing Configuration
Edit .actor/pay_per_event.json to adjust prices:
[
{
"search-web": {
"eventTitle": "Web Search",
"eventDescription": "Live Google/Bing search results",
"eventPriceUsd": 0.02
}
}
]
Architecture
┌─────────────────────────────────────────────────────────┐
│ Apify Platform │
│ ┌─────────────────────────────────────────────────┐ │
│ │ Web Intelligence MCP Server │ │
│ │ ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌────────┐ │ │
│ │ │ Search │ │ Scrape │ │ Leads │ │Company │ │ │
│ │ │ $0.02 │ │ $0.05 │ │ $0.10 │ │ $0.15 │ │ │
│ │ └────┬────┘ └────┬────┘ └────┬────┘ └───┬────┘ │ │
│ │ └─────────────┴───────────┴────────┘ │ │
│ │ │ │ │
│ │ Actor.charge() │ │
│ │ │ │ │
│ │ MCP Server (SSE) │ │
│ └──────────────────────┼──────────────────────────┘ │
│ │ │
│ https://...apify.actor/sse │
└─────────────────────────────────────────────────────────┘
Local Development
# Install dependencies
npm install
# Build
npm run build
# Run with stdio (for testing)
MCP_TRANSPORT=stdio npm start
# Run with SSE (for local HTTP)
npm start
# Server runs on http://localhost:3000/sse
Testing
Test with the MCP inspector:
npx @modelcontextprotocol/inspector node dist/main.js
Why This Wins
- Supply: Near-zero MCP servers on Apify right now
- Demand: Every AI framework adopting MCP (Claude, GPT, Cursor)
- Agentic Payments: Apify handles billing, agents pay autonomously
- Moat: First quality servers get whitelisted in agent configs
- Recurring: Agents run 24/7, every query = billable event
Revenue Potential
| Daily Calls | Monthly Revenue | Your Cut (80%) |
|---|---|---|
| 100 | $500 | $400 |
| 1,000 | $5,000 | $4,000 |
| 10,000 | $50,000 | $40,000 |
Costs: API keys have free tiers, then ~$0.01-0.05 per call
Support
License
MIT - Build your own, publish, profit.
The USB-C moment for AI agents. Deploy today.
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.