AI Web Scraper - Powered by Crawl4AI
Pay $25.00 for 1,000 Results
AI Web Scraper - Powered by Crawl4AI
Pay $25.00 for 1,000 Results
A blazing-fast AI web scraper powered by Crawl4AI. Perfect for LLMs, AI agents, AI automation, model training, sentiment analysis, and content generation. Supports deep crawling, multiple extraction strategies and flexible output (Markdown/JSON). Seamlessly integrates with Make.com, n8n, and Zapier.
Raizen TechnologyActor Metrics
3 monthly users
No reviews yet
No bookmarks yet
Created in Mar 2025
Modified 7 hours ago
You can access the AI Web Scraper - Powered by Crawl4AI programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1# Start Server-Sent Events (SSE) session and keep it running
2curl "https://actors-mcp-server.apify.actor/sse?token=<YOUR_API_TOKEN>&actors=raizen/ai-web-scraper"
3
4# Session id example output:
5# event: endpoint
6# data: /message?sessionId=9d820491-38d4-4c7d-bb6a-3b7dc542f1faUsing AI Web Scraper - Crawl4AI for LLMs, AI Agents & Automation via Model Context Protocol (MCP) server
MCP server lets you use AI Web Scraper - Crawl4AI for LLMs, AI Agents & Automation within your AI workflows. Send API requests to trigger actions and receive real-time results. Take the received sessionId and use it to communicate with the MCP server. The message starts the AI Web Scraper - Crawl4AI for LLMs, AI Agents & Automation Actor with the provided input.
1curl -X POST "https://actors-mcp-server.apify.actor/message?token=<YOUR_API_TOKEN>&session_id=<SESSION_ID>" -H "Content-Type: application/json" -d '{
2 "jsonrpc": "2.0",
3 "id": 1,
4 "method": "tools/call",
5 "params": {
6 "arguments": {
7 "browserConfig": {
8 "browser_type": "chromium",
9 "headless": true,
10 "verbose_logging": false,
11 "ignore_https_errors": true,
12 "user_agent": "random",
13 "proxy": "",
14 "viewport_width": 1280,
15 "viewport_height": 720,
16 "accept_downloads": false,
17 "extra_headers": {}
18 },
19 "crawlerConfig": {
20 "cache_mode": "BYPASS",
21 "page_timeout": 20000,
22 "simulate_user": true,
23 "remove_overlay_elements": true,
24 "delay_before_return_html": 1,
25 "wait_for": "1",
26 "screenshot": false,
27 "pdf": false,
28 "enable_rate_limiting": false,
29 "semaphore_count": 10,
30 "memory_threshold_percent": 70,
31 "word_count_threshold": 200,
32 "css_selector": "",
33 "excluded_tags": [],
34 "excluded_selector": "",
35 "only_text": false,
36 "prettify": false,
37 "keep_data_attributes": false,
38 "remove_forms": false,
39 "bypass_cache": false,
40 "disable_cache": false,
41 "no_cache_read": false,
42 "no_cache_write": false,
43 "wait_until": "domcontentloaded",
44 "wait_for_images": false,
45 "check_robots_txt": false,
46 "mean_delay": 0.1,
47 "max_range": 0.3,
48 "js_code": "",
49 "js_only": false,
50 "ignore_body_visibility": true,
51 "scan_full_page": false,
52 "scroll_delay": 0.2,
53 "process_iframes": false,
54 "override_navigator": false,
55 "magic": false,
56 "adjust_viewport_to_content": false,
57 "screenshot_wait_for": 0,
58 "screenshot_height_threshold": 20000,
59 "image_description_min_word_threshold": 50,
60 "image_score_threshold": 3,
61 "exclude_external_images": false,
62 "exclude_social_media_domains": [],
63 "exclude_external_links": false,
64 "exclude_social_media_links": false,
65 "exclude_domains": [],
66 "verbose": true,
67 "log_console": false,
68 "stream": false
69 },
70 "deepCrawlConfig": {
71 "max_pages": 100,
72 "max_depth": 3,
73 "include_external": false,
74 "score_threshold": 0.5,
75 "filter_chain": [],
76 "url_scorer": {}
77 },
78 "markdownConfig": {
79 "ignore_links": false,
80 "ignore_images": false,
81 "escape_html": true,
82 "skip_internal_links": false,
83 "include_sup_sub": false,
84 "citations": false,
85 "body_width": 80,
86 "fit_markdown": false
87 },
88 "contentFilterConfig": {
89 "type": "pruning",
90 "user_query": "",
91 "threshold": 0.45,
92 "min_word_threshold": 5,
93 "bm25_threshold": 1.2,
94 "apply_llm_filter": false,
95 "semantic_filter": "",
96 "word_count_threshold": 10,
97 "sim_threshold": 0.3,
98 "max_dist": 0.2,
99 "top_k": 3,
100 "linkage_method": "ward"
101 },
102 "userAgentConfig": {
103 "user_agent_mode": "random",
104 "device_type": "desktop",
105 "browser_type": "chrome",
106 "num_browsers": 3
107 },
108 "llmConfig": {
109 "provider": "groq/deepseek-r1-distill-llama-70b",
110 "api_token": "",
111 "instruction": "Summarize content in clean markdown.",
112 "base_url": "",
113 "chunk_token_threshold": 2048,
114 "apply_chunking": true,
115 "input_format": "markdown",
116 "temperature": 0.7,
117 "max_tokens": 4096
118 },
119 "extractionSchema": {
120 "name": "Custom Extraction",
121 "baseSelector": "div.article",
122 "fields": [
123 {
124 "name": "title",
125 "selector": "h1",
126 "type": "text"
127 },
128 {
129 "name": "link",
130 "selector": "a",
131 "type": "attribute",
132 "attribute": "href"
133 }
134 ]
135 }
136},
137 "name": "raizen/ai-web-scraper"
138 }
139}'The response should be: Accepted. You should received response via SSE (JSON) as:
1event: message
2data: {
3 "result": {
4 "content": [
5 {
6 "type": "text",
7 "text": "ACTOR_RESPONSE"
8 }
9 ]
10 }
11}Configure local MCP Server via standard input/output for AI Web Scraper - Crawl4AI for LLMs, AI Agents & Automation
You can connect to the MCP Server using clients like ClaudeDesktop and LibreChat or build your own. The server can run both locally and remotely, giving you full flexibility. Set up the server in the client configuration as follows:
1{
2 "mcpServers": {
3 "actors-mcp-server": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "@apify/actors-mcp-server",
8 "--actors",
9 "raizen/ai-web-scraper"
10 ],
11 "env": {
12 "APIFY_TOKEN": "<YOUR_API_TOKEN>"
13 }
14 }
15 }
16}You can further access the MCP client through the Tester MCP Client, a chat user interface to interact with the server.
To get started, check out the documentation and example clients. If you are interested in learning more about our MCP server, check out our blog post.
