Website RAG Markdown Crawler & Contact Finder MCP
MCP server that crawls websites into LLM-ready Markdown and RAG chunks via Apify
- Pricing
- Freemium
- Platforms
- API, Web
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- today
Similar MCP servers
About Website RAG Markdown Crawler & Contact Finder MCP
Website RAG Markdown Crawler & Contact Finder MCP is a freemium MCP server for web search and scraping. It runs as a hosted remote server, so there is nothing to install locally.
The README describes this as an MCP server that pairs a website-to-Markdown crawler with a B2B contact lookup, both reached through Apify Actors. The crawling side turns single URLs or whole sites, discovered through sitemaps and internal links, into Markdown and token-bounded chunks sized for vector database ingestion.
The hosted endpoint exposes the crawler to MCP clients such as Claude Desktop, Cursor and Windsurf, using an Apify API token for authorization. Output per page includes headings, JSON-LD blocks, internal and external link lists and word or token counts, so an agent can decide what to read next.
The README also lists a second tool that extracts company emails, phone numbers, MX mail providers and tech stack signals from domains. Its free Apify tier returns only five items per run, with the first two unmasked. Developers building retrieval pipelines or sales teams enriching company lists are the intended users.
Install
Run in a terminal
claude mcp add --transport http web-markdown-contacts-mcp 'https://mcp.apify.com/?actors=church_of_loujess/fast-website-content-crawler'Add to Settings → Connectors → Add custom connector
https://mcp.apify.com/?actors=church_of_loujess/fast-website-content-crawlerAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"web-markdown-contacts-mcp": {
"url": "https://mcp.apify.com/?actors=church_of_loujess/fast-website-content-crawler"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"web-markdown-contacts-mcp": {
"type": "http",
"url": "https://mcp.apify.com/?actors=church_of_loujess/fast-website-content-crawler"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"web-markdown-contacts-mcp": {
"serverUrl": "https://mcp.apify.com/?actors=church_of_loujess/fast-website-content-crawler"
}
}
}Add to Grok Bot desktop app → Connect apps → Add a custom connector
https://mcp.apify.com/?actors=church_of_loujess/fast-website-content-crawlerEnter a Name (for example "Website RAG Markdown Crawler & Contact Finder MCP"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.
Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"web-markdown-contacts-mcp": {
"type": "http",
"url": "https://mcp.apify.com/?actors=church_of_loujess/fast-website-content-crawler"
}
}
}Using several servers? Build one config file with the MCP config generator.
Tools this server provides (2)
Taken from the project documentation; the running server may differ.
- crawl_website_to_rag_markdown
- Crawl any website or sitemap into clean LLM-ready Markdown and token-bounded RAG chunks.
- find_company_emails_phones_tech
- Extract company emails, phone numbers, social links, MX provider and B2B technologies from company domains.
What it does
- Markdown page conversion
- Converts each page's main content into Markdown while stripping navigation, footers, scripts and cookie banners.
- Token-bounded RAG chunks
- Splits extracted Markdown along section boundaries into chunks with a configurable target word count.
- Sitemap and BFS discovery
- Finds subpages through sitemap.xml, robots.txt sitemap directives and internal links when multi-page mode is used.
- Single-URL exact reads
- Setting maxPagesPerSite to 1 fetches only the listed URLs without following links.
- Structured page metadata
- Returns titles, headings outline, JSON-LD objects, canonical URLs and internal and external link lists per page.
- Contact and tech lookup tool
- A companion tool extracts company emails, phones and tech stack signals from company domains.
Good for
- Indexing a documentation site into a vector database for a support chatbot
- Giving an AI assistant live access to a website's pages through MCP
- Auditing headings, word counts and Schema.org markup across a client's domain
- Monitoring competitor pricing or changelog pages for changes
- Building a company list enriched with public contact details and tech stack
Pricing
Freemium, from $29 a month
Apify free plan with $5 monthly credit; Starter from $29/mo per the README; crawler billed per result.
Prices change. Check apify.com before you buy.
Website RAG Markdown Crawler & Contact Finder MCP FAQ
How do I scrape only the exact URLs I pass without crawling subpages?
Set maxPagesPerSite to 1. Each URL in startUrls is fetched once and converted without queuing internal links.
Does it parse sitemap.xml and nested sitemap indexes?
Yes. When maxPagesPerSite is above 1 and useSitemap is enabled, it checks robots.txt sitemap directives and /sitemap.xml, including sitemap index children.
Does it stay on the starting domain?
Yes. Crawling stays within the starting domain, and outbound links are recorded in externalLinks without being crawled.
Can I turn off RAG chunks if I only want Markdown?
Yes. Setting includeRagChunks to false returns a leaner payload.
Is Website RAG Markdown Crawler & Contact Finder MCP free?
Website RAG Markdown Crawler & Contact Finder MCP has a free plan, with paid plans for more usage or features. Paid plans start at $29 a month.
How do I add Website RAG Markdown Crawler & Contact Finder MCP to Claude Code?
Run this command in your terminal: claude mcp add --transport http web-markdown-contacts-mcp 'https://mcp.apify.com/?actors=church_of_loujess/fast-website-content-crawler'
What are the best alternatives to Website RAG Markdown Crawler & Contact Finder MCP?
The closest alternatives to Website RAG Markdown Crawler & Contact Finder MCP are Website to Markdown Crawler, Web Scraper & Crawler for RAG (Markdown), Web to Text (Apify) by Dataset Works, Docsieve: Website to Markdown for RAG and URL to Markdown — Clean Page Text, Selectors & Source Links.
Where this comes from
- Description: written from the project's README, the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.