How to use Firecrawl: what you can do with it

3 use cases

• Turn any web page into clean markdown for an LLM

  Scrape a URL and get LLM-ready markdown, HTML, a screenshot or JSON instead of raw HTML.

  • REPO firecrawl/firecrawl
  • Data and analytics
  • Beginner
  View prompt

  Using firecrawl/firecrawl with my API key from an environment variable, scrape <url> to markdown with only the main content, and save it to <file>. Report the token-sized length before and after.

  Share Email me this

• Give Claude Code or Cursor live web search and scraping

  Install the Firecrawl skill or MCP server so your agent can search and read the current web.

  • REPO firecrawl/firecrawl
  • Claude Code
  • Cursor
  • Data and analytics
  • Beginner
  View prompt

  Add the firecrawl/firecrawl MCP server to my <Claude Code or Cursor> config with FIRECRAWL_API_KEY from my environment, restart, and test it by fetching the current docs page for <library>.

  Share Email me this

• Crawl a whole docs site into a knowledge base

  Map every URL on a site, then crawl it to markdown in one job for RAG or offline reading.

  • REPO firecrawl/firecrawl
  • Data and analytics
  • Intermediate
  View prompt

  Use firecrawl/firecrawl to map <docs url>, then crawl up to <n> pages as markdown, save each page to ./kb/<slug>.md, and give me a count of pages and any that failed.

  Share Email me this

Quick start with Firecrawl

1. Check you have what it needs: A Firecrawl API key from the hosted service, or a self-hosted instance; Python, Node.js, or curl; or an MCP client such as Claude Code or Cursor.
2. Open firecrawl/firecrawl on GitHub and read the README and license.
3. Get an API key at Firecrawl.dev
4. Python: from firecrawl import Firecrawl, create app = Firecrawl(api_key="fc-YOUR_API_KEY"), then result = app.scrape('firecrawl.dev')
5. Or from the CLI: firecrawl https://firecrawl.dev --only-main-content
6. Ask for other formats such as structured JSON or screenshots when you need them

These steps come from our top use case, Turn any web page into clean markdown for an LLM, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for firecrawl/firecrawl

claude mcp add --transport http deduped https://dedupedai.com/mcp

Firecrawl alternatives · Best AI repos for Data and analytics

About this repo

• Who it is forDevelopers building AI agents, RAG pipelines or research tools that need clean page content instead of raw HTML.
• Why it is hot195k stars, talked about in 2 AI sources we track
• LanguageTypeScript
• Sourcegithub.com/firecrawl/firecrawl · Back to Hot repos

Requirements

• A Firecrawl API key from the hosted service, or a self-hosted instance
• Python, Node.js, or curl; or an MCP client such as Claude Code or Cursor

Related repos

• Trended earlier REPO openbq-org/OpenBB OpenBB OpenBB's Open Data Platform (ODP) is an open-source toolset that connects proprietary, licensed and public financial data once and exposes it to Python for quants, OpenBB Workspace and Excel for analysts, MCP servers for AI agents and REST APIs for other apps. It installs with pip, includes a command line interface, and can run a local API backend for the OpenBB Workspace.
• Trended earlier REPO Aisland-SJL/dsh-usage DSH Usage dsh-usage is a JavaScript plugin for DeepSeek Harness that adds a persistent balance and token-usage dock, a detail panel, an activity heatmap, and a DSH versus Claude Code usage comparison.
• Trended earlier REPO ashishsinha1602/schemagate Schemagate schemagate is a Python library and local studio page that filters a text-to-SQL schema by the caller's grants, so restricted tables never reach the LLM prompt.