> ## Documentation Index > Fetch the complete documentation index at: https://mintlify.com/D4Vinci/Scrapling/llms.txt > Use this file to discover all available pages before exploring further. # MCP Capabilities > Tools and features available through Scrapling's MCP server Scrapling's MCP server provides six powerful tools for web scraping operations. Each tool is optimized for different use cases and protection levels. ## Available Tools ### get Make stealth HTTP GET requests to fetch web pages. **Best for:** Low to mid protection levels, simple HTTP requests **Parameters:** The URL to request Browser to impersonate (chrome, firefox, safari, etc.) Output format: `markdown`, `html`, or `text` CSS selector to extract specific content Extract only content within `` tag Custom HTTP headers Cookies to include in request Proxy URL (format: "[http://user:pass@host:port](http://user:pass@host:port)") Request timeout in seconds Use real browser headers **Example usage:** ```python theme={null} { "url": "https://example.com", "extraction_type": "markdown", "css_selector": "article.main", "impersonate": "chrome" } ``` ### bulk\_get Fetch multiple URLs concurrently with HTTP GET requests. **Best for:** Scraping multiple pages efficiently **Parameters:** Same as `get`, but accepts `urls` (array) instead of `url` (string). List of URLs to fetch concurrently **Example usage:** ```python theme={null} { "urls": [ "https://example.com/page1", "https://example.com/page2", "https://example.com/page3" ], "extraction_type": "markdown", "impersonate": "firefox" } ``` ### fetch Use Playwright browser automation for JavaScript-heavy sites. **Best for:** Single-page applications, sites requiring JavaScript execution **Parameters:** The URL to fetch Output format: `markdown`, `html`, or `text` Run browser in headless mode Block images, fonts, media for speed boost Wait for no network activity for 500ms Timeout in milliseconds Additional wait time in milliseconds CSS selector to wait for before proceeding State to wait for: `attached`, `detached`, `visible`, `hidden` Use real Chrome installation instead of Chromium Set referer as Google search of domain **Example usage:** ```python theme={null} { "url": "https://spa-website.com", "extraction_type": "markdown", "wait_selector": "div.content-loaded", "network_idle": true, "disable_resources": true } ``` ### bulk\_fetch Fetch multiple URLs with browser automation concurrently. **Best for:** Scraping multiple JavaScript-heavy pages **Parameters:** Same as `fetch`, but accepts `urls` (array) instead of `url` (string). **Example usage:** ```python theme={null} { "urls": [ "https://app1.example.com", "https://app2.example.com" ], "headless": true, "network_idle": true } ``` ### stealthy\_fetch Advanced stealth browser automation with Cloudflare bypass. **Best for:** High protection sites, Cloudflare-protected pages **Parameters:** All `fetch` parameters, plus: Automatically solve Cloudflare challenges Block WebRTC to prevent IP leaks Allow WebGL (recommended for stealth) Add noise to canvas fingerprinting Additional Playwright context settings **Example usage:** ```python theme={null} { "url": "https://protected-site.com", "extraction_type": "markdown", "solve_cloudflare": true, "block_webrtc": true, "hide_canvas": true, "wait": 2000 } ``` ### bulk\_stealthy\_fetch Fetch multiple protected URLs with advanced stealth. **Best for:** Scraping multiple Cloudflare-protected sites **Parameters:** Same as `stealthy_fetch`, but accepts `urls` (array) instead of `url` (string). **Example usage:** ```python theme={null} { "urls": [ "https://protected1.com", "https://protected2.com" ], "solve_cloudflare": true, "network_idle": true } ``` ## Response Format All tools return a structured response: ```python theme={null} { "status": 200, "content": ["Extracted content in requested format"], "url": "https://example.com" } ``` For bulk operations, an array of responses is returned: ```python theme={null} [ { "status": 200, "content": ["Content from URL 1"], "url": "https://example.com/page1" }, { "status": 200, "content": ["Content from URL 2"], "url": "https://example.com/page2" } ] ``` ## Extraction Types Converts HTML to clean Markdown format: ```python theme={null} {"extraction_type": "markdown"} ``` Best for: Readable text, content processing, AI consumption Returns raw HTML content: ```python theme={null} {"extraction_type": "html"} ``` Best for: Preserving structure, further parsing, archival Extracts plain text only: ```python theme={null} {"extraction_type": "text"} ``` Best for: Text analysis, search indexing, minimal data ## CSS Selectors All tools support CSS selectors for targeted extraction: ```python theme={null} # Extract all articles {"css_selector": "article.post"} # Extract main content {"css_selector": "main#content"} # Extract specific elements {"css_selector": "div.product-info"} ``` When `css_selector` matches multiple elements, all matches are returned in the content array. ## Authentication ### HTTP Basic Auth ```python theme={null} { "url": "https://example.com", "auth": { "username": "user", "password": "pass" } } ``` ### Proxy Authentication ```python theme={null} { "url": "https://example.com", "proxy": "http://proxy.example.com:8080", "proxy_auth": { "username": "proxy_user", "password": "proxy_pass" } } ``` ## Common Patterns ```python theme={null} { "url": "https://example.com", "extraction_type": "markdown" } ``` ```python theme={null} { "url": "https://news.example.com/article", "css_selector": "article.content", "extraction_type": "markdown", "main_content_only": true } ``` ```python theme={null} { "url": "https://spa.example.com", "wait_selector": "div.loaded", "network_idle": true, "extraction_type": "html" } ``` ```python theme={null} { "url": "https://protected.example.com", "solve_cloudflare": true, "wait": 2000, "extraction_type": "markdown" } ``` ```python theme={null} { "urls": [ "https://site1.com", "https://site2.com", "https://site3.com" ], "impersonate": "chrome,firefox,safari", "stealthy_headers": true, "extraction_type": "markdown" } ``` ## Tool Selection Guide Use `get` or `bulk_get` for basic HTML pages without JavaScript Use `fetch` or `bulk_fetch` for SPAs and dynamic content Use `stealthy_fetch` or `bulk_stealthy_fetch` for Cloudflare and WAF-protected sites Use bulk variants (`bulk_get`, `bulk_fetch`, `bulk_stealthy_fetch`) for concurrent operations ## Related Documentation Learn about the MCP server Configure MCP server for AI clients