Summary
Converts web pages to clean markdown via an SSE transport, stripping out navigation and boilerplate so you get just the content. Built specifically for RAG pipelines where you need structured text without the noise. Runs as a hosted service at web-scraper.api.klymax402.com and uses x402 micropayments in USDC, so you pay per scrape instead of subscribing. The repository shows it's implemented in TypeScript with MCP tooling but doesn't expose the specific API schema or example calls. Reach for this when you need to ingest web content into a vector database or knowledge base and want someone else to handle the extraction and cleaning.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
6 tools
scrape_urlFetch a URL and extract clean text/markdown content (like readability).2 params
Fetch a URL and extract clean text/markdown content (like readability).
Parameters* required
urlstringURL to scrape
formatstringOutput formatone of
text · markdown · htmldefault: markdownscrape_structuredExtract structured data from a URL using CSS selectors.2 params
Extract structured data from a URL using CSS selectors.
Parameters* required
urlstringURL to scrape
selectorsobjectDict of name → CSS selector (e.g. {"title": "h1.title", "price": ".price"})
screenshot_urlTake a screenshot of a URL.4 params
Take a screenshot of a URL.
Parameters* required
urlstringURL to screenshot
widthintegerViewport widthdefault: 1280
heightintegerViewport heightdefault: 720
full_pagebooleanCapture full scrollable pagedefault: false
extract_linksExtract all links from a URL with their text.2 params
Extract all links from a URL with their text.
Parameters* required
urlstringURL to scrape
filterstringOptional regex pattern to filter URLs
extract_metaExtract metadata from a URL (title, description, OG tags, favicon, etc).1 params
Extract metadata from a URL (title, description, OG tags, favicon, etc).
Parameters* required
urlstringURL to scrape
search_googleSearch Google and return results.2 params
Search Google and return results.
Parameters* required
querystringSearch query
num_resultsintegerNumber of results to returndefault: 10
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Registryactive
TransportSSE
UpdatedMay 16, 2026
