Model Context Protocol

MCP Server for Web Scraping

Give your AI assistant the power to scrape any webpage.
Get HTML, Markdown, or clean text with one tool call.

Works with Claude Desktop, Cursor, VS Code, GitHub Copilot, Claude Code, Cline, and Windsurf.

Works with your favorite AI tools

Claude
Desktop
Cursor
AI Editor
VS Code
+ GitHub Copilot
Claude Code
CLI
Cline
Extension
Windsurf
IDE

Web Scraping Tools for AI: HTML, Markdown, and Text

Three powerful tools to get web content in the format your AI needs.

</>get_web_page_html

Get raw HTML from any webpage. Perfect for parsing structured data, extracting specific elements, or feeding to custom processors.

M↓get_web_page_markdown

Get clean, LLM-ready Markdown. Ideal for feeding content directly to AI models, RAG pipelines, or content analysis.

Aaget_web_page_text

Get plain text without formatting. Best for text analysis, summarization, or when you just need the words.

ScrapingAnt MCP Server for Claude Desktop

Add to your claude_desktop_config.json:
{
  "mcpServers": {
    "scrapingant": {
      "url": "https://api.scrapingant.com/mcp",
      "transport": "streamableHttp",
      "headers": {
        "x-api-key": "YOUR_API_KEY"
      }
    }
  }
}

Quick Setup Steps

1
Get your API key from ScrapingAnt Dashboard
2
Open Claude Desktop settings and edit the config file
3
Paste the config and restart Claude Desktop
Config File Location:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

ScrapingAnt MCP Server for Cursor

Open SettingsMCPAdd new MCP Server and enter:
Name: scrapingant
URL: https://api.scrapingant.com/mcp
Transport: streamableHttp
Headers: x-api-key: YOUR_API_KEY

Quick Setup Steps

1
Open Cursor and go to Settings (⌘ + ,)
2
Navigate to MCPAdd new MCP Server
3
Enter the configuration values and save
Pro Tip:
Cursor will auto-detect the tools. Ask Claude to "scrape a webpage" and it will use the MCP server automatically!

ScrapingAnt MCP Server for VS Code / GitHub Copilot

Add to your VS Code settings or create .vscode/mcp.json:
{
  "mcpServers": {
    "scrapingant": {
      "url": "https://api.scrapingant.com/mcp",
      "transport": "streamableHttp",
      "headers": {
        "x-api-key": "YOUR_API_KEY"
      }
    }
  }
}

Quick Setup Steps

1
Open VS Code settings (JSON) or create .vscode/mcp.json
2
Paste the mcpServers configuration
3
Reload VS Code window to activate
Works with Copilot:
GitHub Copilot Chat can use MCP tools when enabled. Use @workspace to scrape documentation into your context!

ScrapingAnt MCP Server for Claude Code (CLI)

Run this command in your terminal:
claude mcp add scrapingant \
  --transport http \
  https://api.scrapingant.com/mcp \
  -H "x-api-key: YOUR_API_KEY"

Quick Setup Steps

1
Install Claude Code CLI if not already installed
2
Run the command with your API key
3
The MCP server is now available in Claude Code
Terminal Power:
Claude Code can scrape docs directly while coding. Perfect for researching APIs without leaving your terminal!

ScrapingAnt MCP Server for Cline

Add to your cline_mcp_settings.json:
{
  "mcpServers": {
    "scrapingant": {
      "url": "https://api.scrapingant.com/mcp",
      "transport": "streamableHttp",
      "headers": {
        "x-api-key": "YOUR_API_KEY"
      }
    }
  }
}

Quick Setup Steps

1
Install Cline extension from VS Code marketplace
2
Open Cline settings and find MCP configuration
3
Edit the settings file and add the server config
Autonomous Agent:
Cline can use web scraping autonomously during coding tasks. Let it research libraries and APIs on its own!

ScrapingAnt MCP Server for Windsurf

Follow the Windsurf MCP documentation using this config:
{
  "mcpServers": {
    "scrapingant": {
      "url": "https://api.scrapingant.com/mcp",
      "transport": "streamableHttp",
      "headers": {
        "x-api-key": "YOUR_API_KEY"
      }
    }
  }
}

Quick Setup Steps

1
Open Windsurf and access Settings
2
Navigate to Cascade → MCP settings
3
Add the configuration and restart Windsurf
Cascade AI:
Windsurf's Cascade can use MCP tools in Flow mode for seamless web research while coding!

Browser Rendering for MCP Scraping (JavaScript / SPA)

The browser parameter (default: true) enables full headless Chrome rendering for JavaScript-heavy sites.
Single Page Applications (SPAs)
Dynamic content loaded via JavaScript
React, Vue, Angular applications
Infinite scroll and lazy-loaded content
// MCP tool parameters
{
  "url": "https://example.com",
  "browser": true  // default
}

// For static pages, disable browser
{
  "url": "https://example.com",
  "browser": false  // faster
}

Rotating Proxies for MCP Scraping (Datacenter vs Residential)

Datacenter Proxies

Fast and cost-effective. 50K+ IPs. Best for high-volume scraping of sites without aggressive anti-bot protection.
"proxy_type": "datacenter"

Residential Proxies

Higher success rates. 2M+ IPs. Best for sites with anti-bot detection, Cloudflare, or geo-restrictions.
"proxy_type": "residential"

Geo-Targeted MCP Scraping by Country

Target 25+ countries with the proxy_country parameter.
{
  "url": "https://example.com",
  "proxy_type": "residential",
  "proxy_country": "us"  // or uk, de, fr, etc.
}
Pricing

MCP Server Pricing: Credits Usage

MCP requests use standard API credits. Same pricing as our Web Scraping API.

Enthusiast

100.000 API credits

$19
/mo
Ideal for freelancers or students.
Get Started
Email support
All MCP tools included

Startup

500.000 API credits

$49
/mo
For small to medium sized teams looking to grow.

Popular choice!
Get Started
Priority email support
All MCP tools included
Expert assistance

Business

3.000.000 API credits

$249
/mo
For larger teams and companies.
Get Started
Priority support
All MCP tools included
Dedicated manager

Frequently asked questions.

If you have any further questions, Get in touch with our friendly team
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."

Oleg Kulyk,
ScrapingAnt Founder
* Our team will contact you ASAP.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
By browsing this site, you agree to our Cookies Policy