AnyCrawl MCP server

Get the results of a completed crawl job. Retrieve the scraped content and metadata from a completed crawl job. Usage (parameters): - job_id: The crawl job ID (string, required) - skip: Number of results to skip (number, optional, default: 0) Returns: { status, total, completed, creditsUsed, next?, data[] } Examples: - Get all results: { "job_id": "crawl_12345" } - Paginated results: { "job_id": "crawl_12345", "skip": 50 }

Get the status of a crawl job. Check progress, completion status, and statistics for an ongoing or completed crawl job. Usage (parameters): - job_id: The crawl job ID (string, required) Returns: { job_id, status, start_time, expires_at, credits_used, total, completed, failed } Examples: - Check status: { "job_id": "crawl_12345" }

Cancel a running crawl job. Stop an ongoing crawl job and prevent further processing. Usage (parameters): - job_id: The crawl job ID to cancel (string, required) Returns: { success: boolean, message: string } Examples: - Cancel job: { "job_id": "crawl_12345" }

Scrape a single URL and extract content in selected formats. Best for: One known page (articles, docs, product pages). Not recommended for: Multi-page coverage (use anycrawl_crawl) or open-ended discovery (use anycrawl_search). RECOMMENDED: Use 'playwright' engine for best results with dynamic content and modern websites. Usage (parameters): - url: HTTP/HTTPS URL to scrape (string, required) - engine: 'playwright' | 'cheerio' | 'puppeteer' (required, default: 'playwright') - proxy: Proxy URL (string, optional) - formats: Output formats ['markdown'|'html'|'text'|'screenshot'|'screenshot@fullPage'|'rawHtml'|'json'] (optional) - timeout: Request timeout in ms (number, optional) - retry: Enable auto-retry on failure (boolean, optional) - wait_for: Wait in ms for dynamic pages (number, optional) - include_tags: HTML tags to include (string[], optional) - exclude_tags: HTML tags to exclude (string[], optional) - json_options: { schema?, user_prompt?, schema_name?, schema_description? } (optional) - extract_source: 'html' | 'markdown' (optional) Returns: { url, status, jobId?, title?, html?, markdown?, metadata?, timestamp? } Examples: - Recommended: { "url": "https://example.com", "engine": "playwright" } - With JSON extraction: { "url": "https://news.ycombinator.com", "engine": "playwright", "formats": ["markdown"], "json_options": { "user_prompt": "Extract titles", "schema_name": "Articles" } } - With JSON schema extraction: { "url": "https://example.com/article", "engine": "playwright", "json_options": { "schema_name": "Article", "schema_description": "Extract article metadata and content", "schema": { "type": "object", "properties": { "title": { "type": "string" }, "author": { "type": "string" }, "date": { "type": "string" }, "content": { "type": "string" } }, "required": ["title", "content"] } } }

Search the web and optionally scrape results. Best for: Open-ended discovery, finding relevant content. Not recommended for: Known URLs (use anycrawl_scrape) or comprehensive site coverage (use anycrawl_crawl). RECOMMENDED: Use limit=5 for balanced performance and cost. Use 'playwright' engine for scraping results. Usage (parameters): - query: Search query string (string, required) - engine: Search engine 'google' (optional, default: 'google') - limit: Number of results to return (number, optional, default: 5) - offset: Number of results to skip (number, optional, default: 0) - pages: Number of search result pages to process (number, optional) - lang: Language code (string, optional) - country: Country code (string, optional) - safeSearch: Safe search level 0-2 (number, optional) - scrape_options: Options for scraping search results (object, optional) Returns: Array of search results with optional scraped content Examples: - Recommended: { "query": "artificial intelligence news", "limit": 5 } - With scraping: { "query": "TypeScript tutorials", "limit": 5, "scrape_options": { "formats": ["markdown"], "engine": "playwright" } } - Localized search: { "query": "machine learning", "lang": "es", "country": "ES", "limit": 5 }

Crawl an entire website with configurable depth and limits. Best for: Multi-page coverage, site mapping, content discovery. Not recommended for: Single pages (use anycrawl_scrape) or open-ended discovery (use anycrawl_search). RECOMMENDED: Use 'playwright' engine for best results with dynamic content and modern websites. Usage (parameters): - url: Starting URL to crawl (string, required) - engine: 'playwright' | 'cheerio' | 'puppeteer' (required, default: 'playwright') - max_depth: Maximum crawl depth (number, optional, default: 10) - limit: Maximum pages to crawl (number, optional, default: 100) - strategy: Crawl strategy 'all' | 'same-domain' | 'same-hostname' | 'same-origin' (optional, default: 'same-domain') - include_paths: Path patterns to include (string[], optional) - exclude_paths: Path patterns to exclude (string[], optional) - retry: Enable auto-retry on failure (boolean, optional) - poll_seconds: Polling interval for job status (number, optional) - poll_interval_ms: Polling interval in milliseconds (number, optional) - timeout_ms: Job timeout in milliseconds (number, optional) - scrape_options: Nested scrape options for each page (object, optional) Returns: { job_id, status, message } for async jobs Examples: - Recommended: { "url": "https://example.com", "engine": "playwright", "limit": 50 } - Deep crawl: { "url": "https://docs.example.com", "engine": "playwright", "max_depth": 5, "limit": 200 } - Filtered crawl: { "url": "https://blog.example.com", "engine": "playwright", "include_paths": ["/posts/*"], "exclude_paths": ["/admin/*"] }