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.
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。