Skip to main content
Glama
818,731 tools. Updated 2026-11-21 23:54

"A server for crawling web pages and finding subpages" matching MCP tools:

  • Discover all reachable URLs on a site by following links up to a set depth. Returns internal and external link counts, supports keyword filters, SPAs, and per-level limits.
    Apache 2.0
  • Search the web to find relevant web pages on any topic. Returns titles, URLs, snippets, and relevance scores.
    MIT
  • Retrieve a collective's page tree, including landing page and all subpages, to browse or navigate pages by collective ID. Use pagination limits for large collections.
    MIT

Matching MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Pages Native 0.5.0: 36 local MCP tools and a Codex plugin for native Apple Pages on macOS. Guarded text and table edits, structured search, typed model recipes, batches of up to 10 documents, recipe history and restoration, native PDF previews. Uses only the public Pages scripting API; preserves .pages without Word conversion or Accessibility.
    3
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables creating, listing, and deleting temporary shared Markdown/HTML pages with 72-hour expiration. Supports local Node.js or Cloudflare Workers deployment with OAuth login.
    MIT

Matching MCP Connectors

  • Draft, preview and publish landing pages with lead forms from Claude or another MCP client.

  • PagesOAuth

    Páginas, rascunhos, publicação e redirecionamentos

  • Fetch MDN Web Docs or TypeScript handbook pages as markdown using plain names or mdn:/ts: identifiers for quick reference lookup.
    MIT
  • Fetch documentation from a web URL by crawling HTML pages, with configurable depth, pattern, and directory restrictions to add a new source.
    MIT
  • Start a website crawl and immediately receive a crawl ID without waiting for completion; track progress separately and cap pages to control context.
    ISC
  • Extract all outbound hyperlinks from a webpage with their anchor text. Useful for crawling, finding subpages, or mapping site sections.
    -
  • Create new pages in Voog CMS by specifying title, slug, and language. Supports optional parent_id for subpages and node_id for multilingual translations.
    MIT
  • List Productive pages filtered by project, creator, or parent hierarchy. Discover subpages and retrieve page metadata without loading full content.
    MIT
  • Extract and clean links from a webpage: removes tracking parameters and duplicates, optionally filters by keyword or same-site. Useful for crawling documentation or locating a download.
    MIT
  • Convert web pages into clean Markdown by crawling site links or web search results, removing navigation, ads, and footers for RAG, AI agents, documentation import, and content audits.
    MIT
  • Extract sanitized HTML from web pages to analyze structure, identify form fields, and plan automation selectors for web crawling operations.
    MIT
  • Extract all links from a web page as absolute URLs, classified as internal or external, with anchor text and attributes. Supports scope filtering, deduplication, and result limits for crawling or link audits.
    MIT
  • Discover site URLs from robots.txt and sitemap XML without crawling. Get a clean list of published pages for documentation, blog, or product inventory before extraction.
    Apache 2.0
  • Enumerate all internal URLs reachable from a root URL to map site structure and discover pages before crawling. Use include_pattern and limit to filter results.
    MIT