# AI use cases for Firecrawl (firecrawl/firecrawl) Repo: [firecrawl/firecrawl](https://github.com/firecrawl/firecrawl) | Use cases: 3 | Page: https://dedupedai.com/use-cases/firecrawl-firecrawl/ Firecrawl is an API that searches, scrapes, crawls and interacts with the web and returns clean markdown, structured JSON or screenshots for AI agents. It handles JavaScript-heavy pages, proxies and rate limits, parses PDFs and DOCX, can click and type before extracting, and plugs into agents as a skill or an MCP server. It is open source and also offered as a hosted service with an API key. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Turn any web page into clean markdown for an LLM: https://dedupedai.com/use-cases/firecrawl-firecrawl/turn-any-url-into-clean-markdown/ - Give Claude Code or Cursor live web search and scraping: https://dedupedai.com/use-cases/firecrawl-firecrawl/give-your-coding-agent-live-web-access/ - Crawl a whole docs site into a knowledge base: https://dedupedai.com/use-cases/firecrawl-firecrawl/crawl-a-docs-site-into-a-knowledge-base/ ## How to turn any web page into clean markdown for an LLM with Firecrawl Repo: [firecrawl/firecrawl](https://github.com/firecrawl/firecrawl) | Difficulty: Beginner | Time: 10 minutes | Basis: From the README Scrape a URL and get LLM-ready markdown, HTML, a screenshot or JSON instead of raw HTML. **Who it is for:** A developer feeding web pages to a model who is tired of cleaning boilerplate and broken JavaScript pages. **The problem:** Raw HTML wastes tokens and JS-heavy pages often come back empty. **The outcome:** Clean markdown of the page's main content, ready to drop into a prompt or a vector store. ### Steps 1. Get an API key at Firecrawl.dev 2. Python: `from firecrawl import Firecrawl`, create `app = Firecrawl(api_key="fc-YOUR_API_KEY")`, then `result = app.scrape('firecrawl.dev')` 3. Or from the CLI: `firecrawl https://firecrawl.dev --only-main-content` 4. Ask for other formats such as structured JSON or screenshots when you need them ### Prompt to paste into your agent ```text Using firecrawl/firecrawl with my API key from an environment variable, scrape to markdown with only the main content, and save it to . Report the token-sized length before and after. ``` ### Caveat Respect each site's terms and robots rules when scraping. Risk, credentials: Keep the fc- API key in an environment variable, not in code you commit. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/firecrawl-firecrawl/turn-any-url-into-clean-markdown/ ## How to give Claude Code or Cursor live web search and scraping with Firecrawl Repo: [firecrawl/firecrawl](https://github.com/firecrawl/firecrawl) | Difficulty: Beginner | Time: 10 minutes | Basis: From the README Install the Firecrawl skill or MCP server so your agent can search and read the current web. **Who it is for:** A developer whose coding agent keeps guessing at docs that changed last month. **The problem:** Agents answer from stale training data when the library docs moved on. **The outcome:** An agent that can search the web and pull clean page content mid-task. ### Steps 1. Install the skill with `npx -y firecrawl-cli@latest init --all --browser` and restart your agent 2. Or add the MCP server: an mcpServers entry named firecrawl-mcp that runs npx with the firecrawl-mcp package and FIRECRAWL_API_KEY in env 3. Ask the agent to search for the current docs and scrape the relevant page before it writes code ### Prompt to paste into your agent ```text Add the firecrawl/firecrawl MCP server to my config with FIRECRAWL_API_KEY from my environment, restart, and test it by fetching the current docs page for . ``` ### Caveat Risk, credentials: The MCP config holds your API key; keep it out of shared or committed config files. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/firecrawl-firecrawl/give-your-coding-agent-live-web-access/ ## How to crawl a whole docs site into a knowledge base with Firecrawl Repo: [firecrawl/firecrawl](https://github.com/firecrawl/firecrawl) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Map every URL on a site, then crawl it to markdown in one job for RAG or offline reading. **Who it is for:** Someone building a chatbot or search over a product's documentation. **The problem:** Copying a docs site page by page is slow and misses pages. **The outcome:** Markdown for every page of the site, ready to chunk and index. ### Steps 1. Discover pages first with the Map endpoint, optionally with `search` to rank URLs by relevance 2. Start a crawl with a POST to the v2 crawl endpoint with the site URL, a page `limit` and markdown format 3. Poll the returned job ID until the crawl finishes 4. Chunk and index the markdown in your vector store ### Prompt to paste into your agent ```text Use firecrawl/firecrawl to map , then crawl up to pages as markdown, save each page to ./kb/.md, and give me a count of pages and any that failed. ``` ### Caveat Crawls use credits on the hosted plan; set a page limit before you start. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/firecrawl-firecrawl/crawl-a-docs-site-into-a-knowledge-base/