{
  "id": "mcp_io_github_manchittlab_thecrawler_c8093481",
  "kind": "mcp",
  "category": "ferramentas",
  "name": "TheCrawler",
  "tagline": "Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.",
  "body": "Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.",
  "url": "https://github.com/manchittlab/TheCrawler",
  "status": "live",
  "origin": "official",
  "origin_id": "io.github.manchittlab/thecrawler",
  "install": "",
  "source": "https://github.com/manchittlab/TheCrawler",
  "transporte": "local",
  "ns": "io.github.manchittlab",
  "versao": "0.5.8",
  "oficial_status": "active",
  "repo_host": "github.com",
  "topico": "files",
  "linguagem": "TypeScript",
  "licenca": "AGPL-3.0",
  "repo_topics": " agpl apify cheerio crawler llm markdown mcp mcp-server model-context-protocol nodejs playwright rag scraper typescript web-scraping ",
  "repo_slug": "manchittlab/thecrawler",
  "stars": 2,
  "forks": 0,
  "prs_abertos": 0,
  "pushed_at": "2026-07-02T17:48:41Z",
  "repo_estado": "ativo",
  "likes": 0,
  "comments": 0,
  "visits": 0,
  "readme_bytes": 12049,
  "readme_api": "https://agentalog.com/api/listings/mcp_io_github_manchittlab_thecrawler_c8093481/readme",
  "readme_fonte": "repo",
  "created_at": "2026-08-29 04:00:27",
  "updated_at": "2026-08-29 04:00:27",
  "mine": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_manchittlab_thecrawler_c8093481",
  "go": "https://agentalog.com/api/go/mcp_io_github_manchittlab_thecrawler_c8093481",
  "comments_api": "https://agentalog.com/api/listings/mcp_io_github_manchittlab_thecrawler_c8093481/comments",
  "readme_sha": "3a1c2e75c19de9a7c0aa25dbafa10ab38901704936f7b33288189851efb66d6c",
  "readme_em": "2026-08-31 13:17:36",
  "payload": {
    "name": "io.github.manchittlab/thecrawler",
    "title": "TheCrawler",
    "version": "0.5.8",
    "remotes": [],
    "packages": [
      {
        "registryType": "npm",
        "identifier": "thecrawler",
        "version": "0.5.8"
      }
    ],
    "official_status": "active"
  },
  "volatil_em": "2026-09-13 19:01:51"
}