spb/tools-spboucher-ai
Public
1{2 "slug": "firecrawl",3 "name": "Firecrawl",4 "aliases": ["mendableai/firecrawl"],5 "vendor": { "name": "Firecrawl (formerly Mendable)", "slug": "firecrawl", "website": "https://www.firecrawl.dev/" },6 "homepage_url": "https://www.firecrawl.dev/",7 "docs_url": "https://docs.firecrawl.dev/",8 "repo_url": "https://github.com/firecrawl/firecrawl",9 "license_url": "https://github.com/firecrawl/firecrawl/blob/main/LICENSE",10 "pricing_url": "https://www.firecrawl.dev/pricing",11 "product_type": "api-service",12 "product_status": "active",13 "summary": "Web data API that scrapes, crawls, maps and searches websites and returns clean Markdown or structured JSON for LLM pipelines, with an AGPL-licensed self-hostable core",14 "description": "Firecrawl is an API service for turning websites into data that language models can consume. It began as an open-source project from the Mendable team (the GitHub repository moved from `mendableai` to the `firecrawl` organization) and is now a hosted product with an AGPL-3.0-licensed core that can also be self-hosted.\n\nThe API is organized around a few verbs. Scrape fetches one URL and returns Markdown, HTML, links, screenshots, metadata or JSON extracted against a schema; Crawl follows a site recursively and collects every page; Map lists a site's URLs quickly; Search runs a web query and optionally returns page content for each hit; Interact continues a scrape session to click, fill forms and read dynamic content; Parse converts local files such as PDF and Office documents; and an Agent mode gathers data autonomously. The service handles JavaScript rendering, proxies and anti-bot measures and delivers asynchronous results through webhooks. Official SDKs exist for Python and Node.js alongside a CLI, a hosted MCP server for coding agents, and integrations with LangChain, LlamaIndex and other frameworks.\n\nFirecrawl is popular for building retrieval corpora, feeding agents with current web content and monitoring documentation sites. Pricing is credit-based with a free tier, subscription plans, pay-as-you-go top-ups and enterprise agreements.\n\nLimits: the hosted service is proprietary beyond the open core and self-hosting lacks some managed features, credit consumption varies by endpoint and option, and like any scraper it cannot access content that sites block or that requires authenticated sessions it does not have.",15 "capabilities": ["Scrape a URL to Markdown, HTML, links, screenshots or schema-based JSON", "Recursive site crawl with asynchronous jobs and webhooks", "Fast URL discovery with Map", "Web search with optional page content", "Interactive sessions for clicks and form filling", "Document parsing for PDF and Office files", "Python and Node.js SDKs, CLI and MCP server", "Self-hostable open-source core"],16 "workflows": ["Build a RAG corpus from a documentation site", "Feed an agent live web pages in Markdown", "Monitor a set of pages for changes", "Extract product fields into JSON with a schema"],17 "advantages": ["Output tailored to LLM consumption", "One API for scrape, crawl, map and search", "Open core allows self-hosting", "Broad framework and MCP integrations"],18 "limitations": ["Hosted features exceed what the self-hosted core offers", "Credit costs vary by endpoint and option", "Cannot bypass sites that block or require logins", "AGPL obligations apply when modifying and serving the core"],19 "prerequisites": ["API key for the hosted service", "Docker for self-hosting"],20 "audiences": ["Developers building RAG and agent pipelines", "Teams needing clean text from many sites"],21 "alternatives": ["jina-reader", "tavily", "apify", "scrapfly", "crawlee"],22 "comparison_notes": "Jina Reader covers the single-URL-to-Markdown case with a simpler prefix-style API and a search endpoint, without full crawl orchestration. Tavily is primarily a search and extraction API for agents, overlapping on search and extract but not on recursive crawling. Apify offers a marketplace of site-specific scrapers and hosted Actors rather than a generic page-to-Markdown API. Scrapfly is a scraping API centred on anti-bot bypass and raw HTML; Crawlee is an open-source library you run and operate yourself.",23 "categories": [{ "slug": "data-collection-crawling", "primary": true }, { "slug": "search-apis" }],24 "tags": ["crawler", "api", "llm", "rag", "markdown", "self-hosted", "python", "typescript", "mcp"],25 "use_cases": ["crawl-websites", "build-agents", "search-the-web-programmatically"],26 "operating_systems": ["web", "linux"],27 "execution_modes": ["cloud", "self-hosted"],28 "interfaces": ["api", "sdk", "cli", "mcp-server", "web"],29 "deployment_models": ["saas", "on-premises"],30 "integrations": ["LangChain", "LlamaIndex", "OpenAI", "Model Context Protocol", "Cursor", "Claude Code", "Zapier", "n8n"],31 "data_formats": ["Markdown", "HTML", "JSON", "Screenshots", "PDF (input)", "DOCX (input)"],32 "languages": ["Python", "TypeScript", "JavaScript"],33 "source_model": "mixed",34 "license_spdx": "AGPL-3.0-only",35 "pricing_model": ["freemium", "paid", "usage-based", "enterprise"],36 "pricing_checked_at": "2026-11-02",37 "self_hostable": true,38 "sources": [39 { "url": "https://www.firecrawl.dev/", "type": "official_site", "title": "Firecrawl", "supports": ["name", "summary"], "checked_at": "2026-11-02" },40 { "url": "https://docs.firecrawl.dev/introduction", "type": "official_docs", "title": "Firecrawl docs – Introduction", "supports": ["capabilities", "integrations", "data_formats", "description"], "checked_at": "2026-11-02" },41 { "url": "https://www.firecrawl.dev/pricing", "type": "pricing_page", "title": "Firecrawl pricing", "supports": ["pricing_model"], "checked_at": "2026-11-02" },42 { "url": "https://github.com/firecrawl/firecrawl/blob/main/LICENSE", "type": "license_page", "supports": ["license_spdx", "source_model", "self_hostable"], "checked_at": "2026-11-02" }43 ],44 "confidence": "high",45 "discovery_method": "editorial-research",46 "depth": "deep",47 "editorial_status": "reviewed",48 "visibility": "public",49 "featured": false,50 "author": "batch-C"51}52