Fast Website RAG Markdown Crawler & B2B Contact Finder MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| Authorization | No | Bearer token for the remote hosted Apify MCP Gateway, e.g. "Bearer <YOUR_APIFY_API_TOKEN>". | |
| APIFY_API_TOKEN | No | Your Apify API token used as an environment variable for local stdio via npx. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
MCP server combining high-speed Website-to-Markdown RAG crawling with B2B Website Email, Phone, DNS MX verification, and 50+ Tech Stack fingerprinting. Store docs: https://apify.com/church_of_loujess/fast-website-content-crawler
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| crawl_website_to_rag_markdownB | Crawl any website or sitemap into clean LLM-ready Markdown and token-bounded RAG chunks without headless browser overhead. |
| find_company_emails_phones_techB | Extract verified corporate emails, phone numbers, social links, DNS MX deliverability provider, and 50+ B2B technologies from company domains. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools target clearly separate workflows: one crawls websites into Markdown/RAG chunks, while the other extracts B2B contact and technology data from company domains. There is no overlap in purpose or likely inputs, so an agent can easily choose the right tool.
Both names use snake_case and start with clear action verbs (crawl, find), which is consistent overall. The second name is more of a compound noun list and the first includes a directional phrase ('to_rag'), so the pattern is readable but not perfectly uniform.
The server exposes only two tools for two fairly broad capabilities, which feels thin even if each tool is comprehensive. It would benefit from auxiliary operations such as crawl status or batch company lookup to make the surface feel properly scoped.
The tool surface covers both advertised functions—website crawling/RAG chunking and B2B contact/technology extraction—with no obvious dead ends. Minor gaps exist around job/status management, crawl customization, or batch processing, but agents can likely work around them.