KitScout

Categories › Web & Browser › Scraping, crawling & page-to-text

io.github.vanshulgoyal101/mcp

MCP serverGitHub-verified authorRemote● LiveFree to tryField-tested 1/3

Read any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe.

Install

Remote server: your requests and data go to mcp.vanshul.com. Claude Code: claude mcp add --transport http mcp https://mcp.vanshul.com/mcp · Claude app: Settings → Connectors → Add custom connector.

What it can do

The tools this server listed when we connected to it, in its own words.

  • fetch_markdown — Fetch a web page and return its main content as clean Markdown (nav, ads and boilerplate removed). Raw Markdown, plain-text and JSON endpoin
  • fetch_metadata — Fetch a web page and return its metadata as JSON: title, byline, site name, excerpt and word count (no full body).
  • extract_links — Fetch a web page and return all of its outbound http(s) links (with anchor text) as JSON. Useful for crawling or finding related pages.
  • search_page — Fetch a web page and return only the passages that match a query, instead of the whole page. Each result includes its heading breadcrumb and

KitScout test notes

Field test, 2026-11-14: Free web page reader MCP servers. Score 1/3, average response 0.3 s, rank 3 of 6. Fastest, HTML only.

  • PASS en.wikipedia.org/wiki/Model_Context_Protocol
    "...introduced by [Anthropic] in November 2024..."
  • FAIL kitscout.dev/t/view.html?... (JavaScript-only)
    "... [Field tests] [For agents] Loading..."
  • FAIL arxiv.org/pdf/1706.03762
    Error: Page is not a text or HTML document (got application/pdf)

Full results and method

Similar tools