{
  "id": "01-firecrawl",
  "slug": "firecrawl",
  "normalized_name": "firecrawl",
  "name": "Firecrawl",
  "vendor_url": "firecrawl.dev",
  "category": "data-enrichment",
  "what_it_does": "A web scraping and crawling API that turns any URL or whole site into clean markdown or structured JSON for LLM pipelines, with search, map, crawl, extract, parse and browser-interaction endpoints.",
  "ai_features": "The scrape and crawl core is deterministic fetching plus HTML-to-markdown conversion. AI enters in the extract mode (LLM-driven schema extraction from pages), the agent tool (autonomous web research) and the interact tool (natural-language browser actions); the vendor lists those as separate tools from plain scrape.",
  "mcp_status": "official",
  "mcp_url": "https://mcp.firecrawl.dev/v2/mcp (docs: https://docs.firecrawl.dev/mcp-server; repo: https://github.com/firecrawl/firecrawl-mcp-server; search-only endpoint https://mcp.firecrawl.dev/v2/mcp-search; OAuth variant https://mcp.firecrawl.dev/v2/mcp-oauth)",
  "mcp_auth": "api key as an Authorization Bearer header, or browser sign-in via the /v2/mcp-oauth variant, or keyless with daily limits. The vendor docs state \"Configure an API key in your client, no browser needed\" for the key path and describe a \"No account or key\" mode that works \"within daily limits\".",
  "api_gate": "free - the vendor's pricing page states \"Firecrawl gives you 1,000 free credits every month, which covers about 1,000 pages, and no card is required.\" Paid plans are listed at Hobby $16/month, Standard $83/month, Growth $333/month and Scale $599/month (billed yearly), Enterprise custom.",
  "revops_role": "The web-fetch leg of a research or enrichment agent: pull a prospect's site, pricing page or changelog into markdown so a downstream model can extract firmographics, tech stack or trigger events without a data vendor.",
  "tier": "RESEARCHED",
  "last_checked": "2026-09-07",
  "sources": "https://docs.firecrawl.dev/mcp-server, https://www.firecrawl.dev/pricing, https://github.com/firecrawl/firecrawl-mcp-server, https://mcp.firecrawl.dev/v2/mcp",
  "notes": "Verified 2026-09-07: POST of an MCP initialize to https://mcp.firecrawl.dev/v2/mcp with no key returned HTTP 200 with a JSON-RPC result (protocolVersion 2025-03-26, serverInfo name beginning \"firecrawl-\"), which matches the documented keyless mode. The control POST to /zzz-not-a-route on the same host returned 200 with the marketing site's HTML, so the control path is not a discriminator for this host and the JSON-RPC body is the evidence. The repo README lists scrape, map, search, crawl, parse, agent, interact, developer_search, research and monitor tools (14 or more). Firecrawl is a general web-data tool, not a contact database; it is in this category because GTM agents use it as the fetch layer under enrichment, the same reason Exa and Bright Data are here. 2026-09-07: https://mcp.firecrawl.dev/v2/mcp returned 200 with a JSON-RPC initialize result to an MCP initialize POST (https://mcp.firecrawl.dev/v2/mcp).",
  "mcp_status_bucket": "official",
  "api_gate_bucket": "free",
  "mcp_urls": [
    "https://mcp.firecrawl.dev/v2/mcp",
    "https://docs.firecrawl.dev/mcp-server",
    "https://github.com/firecrawl/firecrawl-mcp-server",
    "https://mcp.firecrawl.dev/v2/mcp-search",
    "https://mcp.firecrawl.dev/v2/mcp-oauth"
  ],
  "source_urls": [
    "https://docs.firecrawl.dev/mcp-server",
    "https://www.firecrawl.dev/pricing",
    "https://github.com/firecrawl/firecrawl-mcp-server",
    "https://mcp.firecrawl.dev/v2/mcp"
  ],
  "source_annotations": [],
  "vendor_domain": "firecrawl.dev",
  "display_name": "Firecrawl",
  "docs_url": null,
  "jobs": [],
  "jobs_tagged_by": null,
  "jobs_tagged_on": null,
  "github_url": null,
  "github_stars": null,
  "github_last_commit": null,
  "github_archived": null,
  "github_fetched_on": null,
  "github_candidates": [
    "https://github.com/firecrawl/firecrawl-mcp-server",
    "https://github.com/firecrawl/firecrawl-mcp-server"
  ],
  "docs_digest": null,
  "docs_last_crawled": null,
  "submission": null,
  "mcp_tools": [
    {
      "name": "Arguments",
      "description": "Result",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "Categories",
      "description": "`firecrawl_find_tools`",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "Execute",
      "description": "`firecrawl_scrape`",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "Intent",
      "description": "Tool",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "agent",
      "description": "Multi-source research, unknown or many sites",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "crawl",
      "description": "Multi-page extraction (with limits)",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "developer",
      "description": "Programming questions over developer sources",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "find_tools",
      "description": "Alexandria catalogue browsing and URL lookup",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "firecrawl_parse",
      "description": "\nParse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with `pdfO",
      "required_params": [],
      "evidence": "live-list",
      "repo_party": null,
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "firecrawl_scrape",
      "description": "\nScrape one URL and return its content: markdown by default, or HTML, links, screenshots, branding data, a targeted answer, or JSON matching a supplied schema. Use it when the request identifies a page and needs its content or defined field",
      "required_params": [],
      "evidence": "live-list",
      "repo_party": null,
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "firecrawl_search",
      "description": "\nSearch web, news, or image sources and return ranked results with query-relevant highlights. Each web result is a title, URL, and description; use `firecrawl_scrape` on a result URL when the excerpt is not enough.\n\nAuthenticated search als",
      "required_params": [
        "query"
      ],
      "evidence": "live-list",
      "repo_party": null,
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "interact",
      "description": "Interact with a URL or scraped page",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "map",
      "description": "Discovering URLs on a site",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "monitor",
      "description": "Recurring page checks",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "parse",
      "description": "Files and hosted upload refs",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "research",
      "description": "Paper and GitHub repository research",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "scrape",
      "description": "Single page content",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    },
    {
      "name": "search",
      "description": "Web search for info",
      "required_params": [],
      "evidence": "readme",
      "repo_party": "first-party",
      "source_party": null,
      "risk": "read"
    }
  ],
  "mcp_tool_count": 18,
  "mcp_tools_evidence": "live-list",
  "mcp_tools_repo": "firecrawl/firecrawl-mcp-server",
  "mcp_tools_repo_party": "first-party",
  "mcp_catalog_shape": "fixed",
  "mcp_catalog_note": null,
  "mcp_tools_fetched_on": "2026-09-27",
  "cli_status": "official",
  "cli_party": "first",
  "cli_binary": "firecrawl",
  "cli_install": [
    {
      "cmd": "npm install -g firecrawl-cli",
      "manager": "npm",
      "source_url": "https://docs.firecrawl.dev/sdks/cli",
      "party": "first",
      "fetched_on": "2026-09-27"
    },
    {
      "cmd": "npx -y firecrawl-cli@latest",
      "manager": "npx",
      "source_url": "https://docs.firecrawl.dev/sdks/cli",
      "party": "first",
      "fetched_on": "2026-09-27"
    }
  ],
  "cli_login": "firecrawl login",
  "cli_commands_seen": [
    "agent",
    "browser",
    "config",
    "crawl",
    "credit-usage",
    "developer",
    "init",
    "interact",
    "login",
    "logout",
    "map",
    "monitor",
    "scrape",
    "search",
    "version",
    "view-config"
  ],
  "cli_docs_url": "https://docs.firecrawl.dev/sdks/cli",
  "cli_repo": null,
  "cli_packages": [
    {
      "kind": "npm",
      "package": "firecrawl-cli",
      "version": "1.24.6",
      "party": "first",
      "url": "https://www.npmjs.com/package/firecrawl-cli"
    }
  ],
  "cli_evidence": "vendor-docs",
  "cli_checked_on": "2026-09-27",
  "github_org": "firecrawl",
  "github_org_status": "resolved",
  "github_org_url": "https://github.com/firecrawl",
  "github_org_evidence": {
    "rule": "rule 1",
    "url": "https://github.com/firecrawl/firecrawl-mcp-server",
    "matched_domain": "firecrawl.dev",
    "via": "website",
    "detail": "account website firecrawl.dev has the vendor's domain",
    "confidence": "strong",
    "candidates_rejected": []
  },
  "github_org_repos": 86,
  "github_org_repos_mcp": 3,
  "github_org_repos_cli": 3,
  "github_org_latest_activity": "2026-09-08T15:41:42Z",
  "github_org_recent_repos": [
    {
      "name": "pdf-inspector",
      "url": "https://github.com/firecrawl/pdf-inspector",
      "kind": "other",
      "description": "Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.",
      "stars": 18944,
      "pushed_at": "2026-09-08",
      "latest_release": "v1.18.0"
    },
    {
      "name": "firecrawl-php",
      "url": "https://github.com/firecrawl/firecrawl-php",
      "kind": "sdk",
      "description": null,
      "stars": 2,
      "pushed_at": "2026-09-08",
      "latest_release": null
    },
    {
      "name": "firecrawl",
      "url": "https://github.com/firecrawl/firecrawl",
      "kind": "other",
      "description": "The context API to search, scrape, and interact with the web at scale. 🔥",
      "stars": 177931,
      "pushed_at": "2026-09-08",
      "latest_release": "v2.11.0"
    },
    {
      "name": "firecrawl-docs",
      "url": "https://github.com/firecrawl/firecrawl-docs",
      "kind": "docs-or-examples",
      "description": "Documentation for Firecrawl.",
      "stars": 92,
      "pushed_at": "2026-09-08",
      "latest_release": null
    },
    {
      "name": "firecrawl-mcp-server",
      "url": "https://github.com/firecrawl/firecrawl-mcp-server",
      "kind": "mcp-server",
      "description": "🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.",
      "stars": 7418,
      "pushed_at": "2026-09-08",
      "latest_release": "v3.2.1"
    }
  ],
  "github_org_checked_on": "2026-09-08",
  "mcp_endpoint": null,
  "mcp_docs_url": null,
  "endpoint_status": "not-probed",
  "endpoint_http_status": null,
  "endpoint_last_probed": null,
  "endpoint_wall_note": null,
  "canonical": true,
  "canonical_id": "01-firecrawl",
  "also_listed_in": [],
  "source_file": "01-data-enrichment.md",
  "source_line": 894,
  "file_index": 46,
  "category_num": "01",
  "category_slug": "data-enrichment",
  "category_label": "Data & Enrichment",
  "heading": "Firecrawl",
  "missing_schema_fields": [],
  "extra_fields": {},
  "display_rank": 20
}