Web Scraping Tools for AI: HTML, Markdown, and Text
</>get_web_page_html
M↓get_web_page_markdown
Aaget_web_page_text
ScrapingAnt MCP Server for Cursor
scrapingant
https://api.scrapingant.com/mcp
streamableHttp
x-api-key: YOUR_API_KEY
Quick Setup Steps
ScrapingAnt MCP Server for VS Code / GitHub Copilot
.vscode/mcp.json:{
"mcpServers": {
"scrapingant": {
"url": "https://api.scrapingant.com/mcp",
"transport": "streamableHttp",
"headers": {
"x-api-key": "YOUR_API_KEY"
}
}
}
}
Quick Setup Steps
.vscode/mcp.jsonScrapingAnt MCP Server for Claude Code (CLI)
claude mcp add scrapingant \
--transport http \
https://api.scrapingant.com/mcp \
-H "x-api-key: YOUR_API_KEY"
Quick Setup Steps
ScrapingAnt MCP Server for Cline
cline_mcp_settings.json:{
"mcpServers": {
"scrapingant": {
"url": "https://api.scrapingant.com/mcp",
"transport": "streamableHttp",
"headers": {
"x-api-key": "YOUR_API_KEY"
}
}
}
}
Quick Setup Steps
ScrapingAnt MCP Server for Windsurf
{
"mcpServers": {
"scrapingant": {
"url": "https://api.scrapingant.com/mcp",
"transport": "streamableHttp",
"headers": {
"x-api-key": "YOUR_API_KEY"
}
}
}
}
Quick Setup Steps
Pricing
MCP Server Pricing: Credits Usage
Startup
500.000 API credits
Popular choice!
Frequently asked questions.
What is an MCP server?
MCP (Model Context Protocol) is an open standard that enables AI assistants like Claude to connect with external data sources and tools. An MCP server extends your AI assistant's capabilities - in our case, adding the ability to scrape any webpage and return the content as HTML, Markdown, or plain text.
Which AI tools support MCP?
Our MCP server works with Claude Desktop, Cursor, VS Code (with GitHub Copilot), Claude Code (CLI), Cline, and Windsurf. Any tool that supports the Model Context Protocol standard can use our server.
How do I get an API key?
Sign up for a free ScrapingAnt account at app.scrapingant.com/signup. You'll get 10,000 free API credits. Your API key will be available in your dashboard under the API section.
What's the difference between HTML, Markdown, and Text tools?
get_web_page_html returns raw HTML - best for parsing structured data or when you need full DOM access. get_web_page_markdown returns clean Markdown - ideal for feeding directly to LLMs or RAG pipelines. get_web_page_text returns plain text - best for simple text analysis or summarization tasks.
Does it handle JavaScript-rendered pages?
Yes! The browser parameter (default: true) enables full headless Chrome rendering. This handles SPAs, React/Vue/Angular apps, infinite scroll, and any JavaScript-heavy content. For static pages, set browser=false for faster responses.
How do proxy options work?
Use proxy_type="datacenter" for fast, cost-effective scraping (50K+ IPs). Use proxy_type="residential" for sites with anti-bot protection (2M+ IPs). Add proxy_country (e.g., "us", "uk", "de") to target specific geographic regions.
How much does it cost?
MCP requests use standard API credits, same as our Web Scraping API. Start free with 10,000 credits. Paid plans start at $19/month for 100,000 credits. See the pricing section above for full details.
"Our clients are pleasantly surprised by the response speed of our team."
ScrapingAnt Founder