{
  "id": "scrape-web-page-for-facts",
  "task": "Scrape a web page for facts",
  "description": "Fetch and structure an arbitrary public page. The general-purpose fallback when no structured provider has the record.",
  "example_requests": [
    "scrape this page",
    "read a website and extract facts",
    "crawl the open web for this answer",
    "browse and structure a page"
  ],
  "html_url": "https://gtmmcps.com/jobs/scrape-web-page-for-facts",
  "json_url": "https://gtmmcps.com/data/solutions/scrape-web-page-for-facts.json",
  "snapshot_date": "2026-10-17",
  "evidence_note": "Vendor-reported task matches, not a performance ranking or proof of MCP capability. Confirm current requirements and test the intended workflow.",
  "tools": [
    {
      "id": "01-bright-data",
      "name": "Bright Data",
      "capability": "A general-purpose web-scraping/proxy infrastructure platform (residential proxies, browser automation, structured scraping APIs) that GTM engineers repurpose to pull LinkedIn, company-site, and directory data when off-the-shelf enrichment providers lack a record.",
      "api_access": "paid",
      "mcp_support": "official",
      "last_checked": "2026-08-24",
      "sources": [
        "https://github.com/brightdata/brightdata-mcp",
        "https://mcpservers.org/servers/brightdata/brightdata-mcp",
        "https://brightdata.com/pricing/mcp-server"
      ],
      "record_url": "https://gtmmcps.com/tools/01-bright-data"
    },
    {
      "id": "01-clay",
      "name": "Clay",
      "capability": "A spreadsheet-style workflow/orchestration tool that runs lead and company records through \"waterfall\" lookups across 100-200+ third-party data providers (Apollo, Lusha, Clearbit, etc.) and chains automation steps (\"recipes\") to build, enrich, and route prospect lists into a CRM or sequencer.",
      "api_access": "paid",
      "mcp_support": "official",
      "last_checked": "2026-09-03",
      "sources": [
        "https://www.clay.com/mcp",
        "https://university.clay.com/docs/mcp-settings",
        "https://github.com/shanefirek/clay-mcp-public",
        "https://www.landbase.com/blog/clay-pricing",
        "https://www.warmly.ai/p/blog/clay-pricing",
        "https://michaelsaruggia.com/blog/clay-pricing-change-2026",
        "https://www.clay.com/integrations/action/find-a-persons-linkedin-via-name-and-company-smarte"
      ],
      "record_url": "https://gtmmcps.com/tools/01-clay"
    },
    {
      "id": "01-diffbot",
      "name": "Diffbot",
      "capability": "A web-extraction and \"Knowledge Graph\" company that crawls the public web and structures it into an entity graph (organizations, people, articles) queryable for company/entity enrichment, plus raw article/page-extraction APIs.",
      "api_access": "free",
      "mcp_support": "official",
      "last_checked": "2026-08-24",
      "sources": [
        "https://github.com/diffbot/diffbot-mcp",
        "https://www.diffbot.com/pricing",
        "https://www.diffbot.com/products/knowledge-graph"
      ],
      "record_url": "https://gtmmcps.com/tools/01-diffbot"
    },
    {
      "id": "01-exa",
      "name": "Exa",
      "capability": "A search API that returns web pages and structured results ranked by semantic/meaning similarity to a query (embeddings-based) rather than keyword matching, plus tools to fetch page contents and get LLM-generated answers with citations; used in GTM stacks (e.g., Clay) as a research layer to pull live company and person info off the open web.",
      "api_access": "free",
      "mcp_support": "official",
      "last_checked": "2026-09-03",
      "sources": [
        "https://github.com/exa-labs/exa-mcp-server",
        "https://exa.ai/mcp",
        "https://exa.ai/pricing",
        "https://exa.ai/docs/reference/pricing"
      ],
      "record_url": "https://gtmmcps.com/tools/01-exa"
    },
    {
      "id": "05-intently",
      "name": "Intently (getintently.com)",
      "capability": "Scrapes LinkedIn in real time (without an official API or user accounts) to extract profile/company data, competitor followers, and post reactions/comments as engagement signals.",
      "api_access": "paid",
      "mcp_support": "none-found",
      "last_checked": "2026-09-02",
      "sources": [
        "https://getintently.com"
      ],
      "record_url": "https://gtmmcps.com/tools/05-intently"
    },
    {
      "id": "02-phantombuster",
      "name": "PhantomBuster",
      "capability": "General browser-automation/data-extraction platform (\"Phantoms\") that runs cloud scripts to scrape and act on LinkedIn and other web platforms - widely used as a LinkedIn outbound backbone rather than a purpose-built sequencer.",
      "api_access": "paid",
      "mcp_support": "official",
      "last_checked": "2026-09-03",
      "sources": [
        "https://hub.phantombuster.com/docs/mcp-server",
        "https://lagrowthmachine.com/phantombuster-pricing/",
        "https://github.com/globodai-group/mcp-phantombuster",
        "https://phantombuster.com/automations/linkedin/4015/linkedin-profile-url-finder",
        "https://support.phantombuster.com/hc/en-us/articles/26971028103826-How-to-Use-the-LinkedIn-Profile-URL-Finder"
      ],
      "record_url": "https://gtmmcps.com/tools/02-phantombuster"
    }
  ]
}