Pricing

Pay per event + usage

Try for free

Go to Apify Store

Web Content & URL Tools MCP Server

Try for free

MCP server for AI agents (32 tools): web pages & batch URLs to Markdown, all-in-one SEO/tech/security/AI-search (GEO) audits, B2B lead & contact extraction, phishing URL risk checks, SSL, DNS, SPF/DMARC, SAML/OIDC, developer utilities and Hyperliquid data.

Pricing

Pay per event + usage

Rating

0.0

(0)

Developer

Avalon

Actor stats

Bookmarked

Total users

Monthly active users

5 days ago

Last modified

Tools

Complete Audits & High-Value Workflows (Composite Tools)

Tool	What it returns	Price
`audit_competitor_website`	Complete one-stop audit: on-page SEO score & issues, detected technology stack (CMS, CDN, analytics), Open Graph metadata, and content outline	$0.01
`verify_domain_security`	Comprehensive domain security & trust check: TLS/SSL validity & expiry, HTTP security headers grade (A+ to F), and email authentication (SPF, DMARC, MX)	$0.01
`audit_ai_search_readiness`	AI Search (GEO) & LLM crawler readiness: robots.txt permissions for GPTBot/ClaudeBot/PerplexityBot, `/llms.txt` check, static Markdown readability & JSON-LD	$0.01
`extract_company_leads`	B2B lead & contact enrichment: business emails, phone numbers, social profiles (LinkedIn, X, GitHub, YouTube), key pages (pricing/contact) and tech stack	$0.01
`check_url_phishing_risk`	Phishing & scam URL risk score (0–100): redirect chain, Punycode (`xn--`) spoofing, TLS trust and WHOIS domain registration age (< 30 days alert)	$0.01
`audit_prompt_injection_risk`	Indirect prompt injection & hidden text audit: detects system prompt overrides, developer mode triggers, hidden CSS (0px font, display:none), zero-width characters and comments	$0.01
`batch_to_markdown`	Fetch up to 10 web pages in parallel and convert each into clean, LLM-ready Markdown	$0.015
`crawl_and_map_site`	Auto-traverse sitemap or internal documentation links and bundle up to 10 pages into LLM-ready clean Markdown in one shot	$0.015

Page and Web Tools

Tool	What it returns	Price
`to_markdown`	Clean, LLM-ready Markdown of the main content (menus, ads and footers removed), word and character counts, language	$0.003
`get_metadata`	Title, description, preview image, site name, canonical URL, favicon, author, publish time, Open Graph / Twitter tags	$0.003
`extract_structure`	Heading outline, links (internal/external), images, tables and JSON-LD	$0.003
`detect_technologies`	CMS, framework, e-commerce platform, CDN, analytics and payment tools, with evidence	$0.003
`verify_lead_deliverability`	B2B lead email validation: syntax, 50+ disposable providers, role-based mailbox check, MX DNS and safe live SMTP handshake	$0.003
`trace_redirects`	Every redirect hop (HTTP and meta refresh) to the final URL — expands short links	$0.001
`check_ssl`	Certificate issuer, expiry, days remaining, SANs, and whether browsers trust it (with the reason)	$0.001
`grade_security_headers`	A+ to F grade for eight security headers, information leaks and insecure cookies	$0.001
`parse_robots`	robots.txt rules per user agent, sitemaps, and whether a given path may be crawled	$0.001
`parse_sitemap`	URLs from a sitemap or sitemap index (auto-discovered from a site URL, gzip supported)	$0.001
`lookup_domain`	WHOIS (RDAP) registrar, created/expiry dates, domain age, nameservers, DNS records, MX/SPF/DMARC	$0.001
`audit_seo`	On-page SEO score and grade with prioritised issues and fixes	$0.003
`check_broken_links`	Up to 100 links checked: broken, redirected and bot-blocked reported separately	$0.003
`read_feed`	RSS, Atom or RDF feed as JSON (auto-discovered from a website URL)	$0.001
`check_email_domain`	MX, SPF (10-lookup limit), DMARC, DKIM, MTA-STS, TLS-RPT and BIMI graded pass/warn/fail with fixes and a 0-100 score	$0.003
`analyze_saml_metadata`	SAML metadata (XML or URL): entity ID, IdP/SP endpoints and bindings, NameID formats, signing certificate expiry and issues	$0.001
`check_oidc_provider`	OpenID Connect discovery and JWKS: issuer match, HTTPS, PKCE S256, ID token algorithms, key sizes and certificate expiry	$0.001

Developer tools

Tool	What it returns	Price
`parse_cron`	Valid or not, plain-English explanation, previous and next run times in any time zone	$0.001
`test_regex`	Every match with positions and groups, plus find-and-replace; runaway patterns stop in 0.1 s	$0.001
`convert_color`	HEX, RGB, HSL, HSV, CMYK, best text color, contrast and palettes	$0.001
`check_color_contrast`	WCAG 2 contrast ratio with AA/AAA pass/fail	$0.001
`inspect_unicode`	Per-character code point, name and bytes; grapheme count; normalization forms	$0.001
`convert_timezone`	One time in many IANA zones with offsets, abbreviations and DST	$0.001
`list_timezones`	IANA time zone names, optionally by region	$0.001

Hyperliquid perpetuals

Tool	What it returns	Price
`hyperliquid_markets`	Mark/oracle price, 24h change, hourly and annualized funding, open interest, volume	$0.001
`hyperliquid_funding_history`	Hourly funding history (up to 30 days) with average and annualized rate	$0.001
`hyperliquid_candles`	OHLCV candles from 1 minute to 1 week	$0.001

Hyperliquid data comes from Hyperliquid's public market data; this server is not affiliated with Hyperliquid and nothing it returns is financial advice.

You only pay for successful calls. Errors (invalid URL, blocked site, timeout) are free and come back with a clear reason.

Connect

Use the Standby URL with your Apify API token in any MCP client (Claude Desktop, Claude Code, Cursor, VS Code and others):

{
  "mcpServers": {
    "web-content-url-tools": {
      "url": "https://avalonai--web-content-url-tools-mcp.apify.actor/mcp",
      "headers": { "Authorization": "Bearer <YOUR_APIFY_TOKEN>" }
    }
  }
}

Good to know

Every tool declares an output schema, so MCP clients receive typed, structured JSON results.
Pages are read from the HTML the server sends; sites that build everything in the browser return little text and say so in warning.
Some sites block automated access; those calls return target_blocked and are not charged.
Only public http/https addresses are fetched; private and internal addresses are refused.
Korean platforms (Cafe24, Imweb, Naver, Kakao, Channel.io, Toss Payments) are detected alongside global ones, and Naver Blog posts are read from their inner frame automatically.

Web Search MCP Server

quodlibetical_buffalo/web-search-mcp

Search the web with Bing and get titles, URLs, and snippets. MCP server for AI agents.

Marek Pommier

Website Content Crawler — Text, Markdown & AI Chunks

agency-shift/web-content-crawler

Extract text or clean Markdown from public HTML websites. Create source-linked sections for AI knowledge bases while keeping one row per page. Preserve headings, code and tables; inspect a crawl report for failed URLs and truncated content. No JavaScript rendering.

Mako

Web Article Content Extractor

vulnv/web-article-content-extractor

Extract clean, readable content from news articles, blog posts, and web pages. Batch process multiple URLs, download images, bypass bot protection with proxy support. Perfect for content curation, research, and data analysis.

VulnV

Website Content Crawler Pro

datascoutapi/website-content-crawler-pro

Crawl websites and extract clean, structured content in Markdown, JSON, or plain text for AI models, LLMs, vector DBs, or RAG pipelines. Fast, reliable, and stealthy, with bulk processing, advanced metadata extraction, and seamless integration with LangChain, LlamaIndex, and AI workflows.

halam

575

3.7

(3)

Web Fetch

apify/web-fetch

Download any web page by URL and convert it to clean Markdown, plain text, HTML, and other formats. Automatically renders JavaScript and works around bot blocking. The Actor provides a real-time API for quick response times.

Apify

55K

5.0

(4)

Tavily MCP Server

agentify/tavily-mcp-server

Advanced web search and data extraction capabilities through the Tavily API, providing real-time web search, intelligent data extraction, website mapping, and web crawling tools.

agentify

248

Gemini AI MCP SERVER

bhansalisoft/gemini-ai-mcp-server

Gemini AI MCP SERVER unique tool for Gamini AI functionality integration with apify and other AI tool.

bhansalisoft

Web Content Extractor API — URL to JSON

george.the.developer/web-content-extractor-api

Extract structured JSON from any webpage. Articles, products, recipes, jobs. Auto-detects content type. Returns metadata, headings, images, links. For AI agents and RAG.

George Kioko

Web Crawler & Semantic Schema-Enhanced Extractor

devil_port369-owner/web-crawler

Depth-controlled web crawler that transforms websites into structured analytics-ready data. Starting from one or more URLs, it crawls internal links up to a configurable depth and outputs detailed JSON records per page