Claude MarketplacesSubmit
br0ski777 avatar

Web Scraper to Markdown API

br0ski777/web-scraper-x402

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.

tools
6
transport
SSE
last updated
May 16, 2026
View on GitHub

Tools

6 tools

Public tool metadata for what this MCP can expose to an agent.

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
formatstring
Output formatone of text · markdown · htmldefault: markdown
urlstring
URL to scrape
scrape_structuredExtract structured data from a URL using CSS selectors.2 params

Extract structured data from a URL using CSS selectors.

Parameters* required
selectorsobject
Dict of name → CSS selector (e.g. {"title": "h1.title", "price": ".price"})
urlstring
URL to scrape
screenshot_urlTake a screenshot of a URL.4 params

Take a screenshot of a URL.

Parameters* required
full_pageboolean
Capture full scrollable pagedefault: false
heightinteger
Viewport heightdefault: 720
urlstring
URL to screenshot
widthinteger
Viewport widthdefault: 1280
extract_linksExtract all links from a URL with their text.2 params

Extract all links from a URL with their text.

Parameters* required
filterstring
Optional regex pattern to filter URLs
urlstring
URL to scrape
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
urlstring
URL to scrape
search_googleSearch Google and return results.2 params

Search Google and return results.

Parameters* required
num_resultsinteger
Number of results to returndefault: 10
querystring
Search query

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

Web Scraper to Markdown API

MCP Server x402 License: MIT

Extract clean markdown from any URL. Strips nav/ads/scripts, returns structured content. Built for RAG pipelines and AI research agents. Pay-per-call via x402 (USDC on Base L2) -- no API key, no signup, no rate-limit wall.

Part of the klymax402 marketplace -- 100 x402 micropayment APIs for AI agents, one wallet, USDC on Base.

Quickstart -- MCP

Add to your MCP client config (Claude Desktop, Cursor, ElizaOS, etc.):

{
  "mcpServers": {
    "web-scraper": {
      "url": "https://web-scraper.api.klymax402.com/mcp"
    }
  }
}

Quickstart -- HTTP (x402)

curl "https://web-scraper.api.klymax402.com/api/scrape?url=https://example.com"
# -> 402 Payment Required, with an x402 payment challenge in the response body

View the full README on GitHub

Details

Repository
github.com/br0ski777/web-scraper-x402
Website
github.com/Br0ski777/web-scraper-x402
Categories
Web & Browser Automation, AI & LLM Tools, Documents & Knowledge, Search & Web Crawling
Transport
SSE
Registry
MCP registry, active

More from br0ski777

Related Web & Browser Automation MCP servers

View all
1k11-software-solutions avatark11 Playwright QAk11-software-solutions/k11techlab-playwright-qa-mcpUser stories to verified Playwright tests, and self-healing locators with an audit trail.0stars
2k11-software-solutions avatark11 Selenium QAk11-software-solutions/k11techlab-selenium-qa-mcpSelenium tests from user stories (Python or Java) and self-healing locators with an audit trail.0stars
3lembagang avatarHeadless Oraclelembagang/headless-oracle-v5Ed25519-signed market open/close receipts for NYSE, NASDAQ, LSE, JPX, Euronext, HKEX, and SGX.0stars
4lembagang avatarHeadless Oracle Mcplembagang/headless-oracle-v5Ed25519-signed market-state receipts for 28 exchanges. Fail-closed pre-trade gate.0stars
5clauxel avatarChromedevtoolsmcp Mcpclauxel/chrome-devtools-session-mcp-mcpA paid remote MCP for AI agent browser DevTools MCP, built to return verdicts, receipts, usage logs,0stars
6h4ckf0r0day avatarObscurah4ckf0r0day/obscuraThe headless browser for AI agents and web scraping. Rust, anti-detection, CDP-compatible, with a built-in MCP server.15.7Kstars