Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ScrapeAPI MCP Server Scrape https://blog.scrapeapi.dev and return the main article text"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Web scraping tools for Claude and other MCP-compatible LLM agents.
Tool | Description |
| Scrape any URL and return text, links, images, metadata |
| Scrape up to 10 URLs in parallel |
| Extract specific fields using CSS selectors |
| Full-page screenshot as base64 PNG |
| Check remaining credit balance |
| Browse available pre-built datasets |
Related MCP server: Web Scraper MCP Server
Get your API key at https://getscrapeapi.com
Open your Claude Desktop config file:
Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Add this:
{
"mcpServers": {
"scrapeapi": {
"command": "npx",
"args": ["-y", "@scrapeapi/mcp"],
"env": {
"SCRAPEAPI_KEY": "sk_your_api_key_here"
}
}
}
}Restart Claude Desktop
Once connected, just ask Claude:
"Scrape https://example.com and summarize the content"
"Extract all product prices from https://shop.example.com"
"Take a screenshot of https://dashboard.example.com"
"What datasets do you have available?"
Variable | Required | Description |
| Yes | Your ScrapeAPI key |
| No | Override API base URL |
API Docs: https://getscrapeapi.com/docs
Pricing: https://getscrapeapi.com/#pricing
Support: hello@getscrapeapi.com
Check the remaining scrape credits on the current API key. Use before running large scraping jobs to confirm sufficient balance.
Inputs: no named parameters.
Scrape a URL and extract specific fields using CSS selectors. Use when you need structured data from a known page layout (e.g. product price, article title, table data).
Inputs: url (required), fields (required), javascript.
List all available pre-built datasets. Use when the user wants ready-made data without scraping (jobs, real estate, prices, VC funding, etc.)
Inputs: category.
Scrape multiple URLs in parallel and return results for each. Use when you need to compare or aggregate data from several pages.
Inputs: urls (required), extract_text, extract_links, extract_metadata, +1 more.
Scrape any public URL and return structured data: text, links, images, and metadata. Automatically detects whether JavaScript rendering is needed. Use this when you need to read the content of a webpage.
Inputs: url (required), extract_text, extract_links, extract_images, +5 more.
Take a full-page screenshot of a URL and return it as a base64-encoded PNG. Use for visual verification, capturing charts, or archiving page appearances.
Inputs: url (required), wait_for, timeout.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool targets a distinct function: account credits, general scraping, structured extraction, bulk scraping, pre-built datasets, and screenshots. No overlapping purposes.
All tools use consistent snake_case with verb_noun pattern (check_credits, extract_structured, list_datasets, etc.), making them predictable.
Six tools cover the essential capabilities of a scraping API without being excessive. The scope is well-defined and each tool earns its place.
The tool set covers core scraping workflows (single, multiple, structured, screenshots, credit checks, and pre-built datasets). Minor gaps like dataset management exist but don't hinder typical use.
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Web data for agents. Extract web pages, crawl websites, discover URLs, and search the web.
Unblocking and fresh web data for agents: URL to Markdown, YouTube, Maps, Amazon, jobs. Pay per call
Markdown scrape, site map, page metadata, screenshots, web search and PDF to text. Pay per call
