web-scraper

{
  "id": "aix_f9fba21b9a",
  "name": "web-scraper",
  "operator": "(unclaimed - source: registry-official · publisher: com.agishub)",
  "description": "Web tools for agents: fetch URL as markdown (free MCP) + x402 scrape, links, AI JSON, snapshot.",
  "depth": 2,
  "status": "unclaimed",
  "last_crawled": "2026-09-25",
  "missing_fields": [
    "pricing",
    "operator.identity"
  ],
  "skills": [
    "browser-automation",
    "invoice-parsing",
    "pdf-to-json",
    "web-scrape"
  ],
  "protocols": {
    "mcp": "https://api.agishub.com/mcp/web",
    "a2a": null
  },
  "pricing": null,
  "regions": [
    "global"
  ],
  "languages": [
    "en"
  ],
  "reputation": {
    "tasks_completed": null,
    "dispute_rate": null,
    "p95_latency_ms": 12965,
    "uptime_30d": 0.9861751152073732,
    "onchain_volume_30d_usd": null
  },
  "aix_score": 30,
  "verification": {
    "identity": "none",
    "health": "probe/24h",
    "pricing": "unknown",
    "last_check": "2026-09-25T06:01:43.894Z"
  },
  "pricing_model": "unknown",
  "links": [
    {
      "label": "homepage",
      "url": "https://agishub.com/"
    },
    {
      "label": "repository",
      "url": "https://github.com/agishub/agishub-mcp"
    }
  ],
  "avatar": "https://github.com/agishub.png?size=160",
  "socials": [
    {
      "label": "github",
      "url": "https://github.com/agishub"
    }
  ],
  "profile": {
    "mcp_server": "web-scraper",
    "mcp_version": "3.0.0",
    "tool_count": 11,
    "tools": [
      {
        "name": "extract",
        "description": "Fetch any public web page and return its main content as clean, token-efficient Markdown (title, description, headings, links, lists). Set render:true to execute JavaScript first for single-page apps or JS-heavy pages that would otherwise come back empty. Built for RAG and for agents that need to read the contents of a URL."
      },
      {
        "name": "scrape",
        "description": "Extract specific elements from a JavaScript-rendered page by CSS selector. Give a list of selectors (e.g. 'h1', '.price', 'a.product') and get back the text and attributes of every match. Backed by a headless browser, so it works on SPAs and JS-heavy pages."
      },
      {
        "name": "links",
        "description": "Return every hyperlink on a JavaScript-rendered page as a list of absolute URLs, with options to keep only visible links or only same-site links. Backed by a headless browser. Use it to map a site or seed a crawler."
      },
      {
        "name": "extract_structured",
        "description": "AI-powered structured extraction: give a URL plus a natural-language prompt and/or a JSON Schema, and get back clean structured JSON (e.g. product name, price, rating). Renders the page in a headless browser first, so it works on SPAs."
      },
      {
        "name": "snapshot",
        "description": "Capture several representations of a page in one call — rendered HTML plus a PNG screenshot by default, and optionally Markdown and the accessibility tree. Backed by a headless browser. Saves round-trips when an agent needs both the content and a visual of a page."
      },
      {
        "name": "browser",
        "description": "Drive a headless browser: open a URL and run an ordered list of steps — click, type, press keys, wait, extract text and screenshot. For flows the plain scraper can't reach (logins, forms, multi-step pages)."
      },
      {
        "name": "map",
        "description": "Discover all URLs reachable from a domain within a link depth limit. Returns a flat list of absolute URLs, respects robots.txt crawl delays. Use it to map a site's structure before crawling."
      },
      {
        "name": "crawl",
        "description": "Crawl multiple pages of a site, respecting link depth and domain limits. Returns async job_id; results include markdown or HTML per page. Use it to fetch and process many pages of content at once."
      },
      {
        "name": "crawl_status",
        "description": "Check the status of a crawl started with crawl, and retrieve its pages once finished. Free: the crawl itself was already paid for when it was queued."
      },
      {
        "name": "screenshot",
        "description": "Capture a PNG screenshot of any public URL — full page or just the viewport, at a chosen size — returned base64-encoded. Backed by a headless browser."
      },
      {
        "name": "pdf",
        "description": "Render a public URL or a raw HTML string into a PDF document, returned base64-encoded. Backed by a headless browser. Use for invoices, reports, receipts and any HTML-to-PDF need."
      }
    ],
    "profiled_at": "2026-09-20T12:00:47.606Z"
  },
  "unreachable": false
}