Firecrawl for Claude, Cursor, ChatGPT & agents

Firecrawl v2 — scrape a single URL into clean Markdown / HTML / links / screenshots, crawl an entire site with depth / page limits, run a web search with optional page-content scraping, map a websi...

curl -fsSL https://syncorelabs.ai/install.sh | sh

What it does

Firecrawl v2 — scrape a single URL into clean Markdown / HTML / links / screenshots, crawl an entire site with depth / page limits, run a web search with optional page-content scraping, map a website to discover URLs, and extract structured data using AI-driven autonomous extraction. Use when the user mentions Firecrawl, scrape, crawl, web scraping, page content, headless browser, structured extraction, or wants to pull / harvest text from websites for an LLM. IMPORTANT: For exploring multiple pages or sub-pages, use crawl_site — do NOT call scrape_url repeatedly.

The Firecrawl skill is one of 75+ pre-wired Syncore integrations that any MCP-compatible client — Claude Desktop, Claude Code, Cursor, Windsurf, Codex CLI, and ChatGPT desktop — can call out of the box. You don't configure MCP servers or copy API keys into a JSON file; the Syncore daemon discovers the skill at startup and exposes its tools to whichever AI client is running.

Sample prompts

Once Syncore is installed and Firecrawl is connected, ask your agent something like:

• “Scrape syncorelabs.ai/blog and return clean markdown of the latest post.”
• “Crawl docs.anthropic.com up to depth 2 and extract all H2 headings.”
• “Extract pricing data from these three SaaS pages into a structured JSON.”

Tools available (9)

• firecrawl__scrape_url

  Scrape a SINGLE URL for raw content (Markdown, HTML, screenshot, etc.). ONLY use this for one specific page. If the user wants to explore multiple pages, sub-pages, or crawl a site, use crawl_site instead — do NOT call scrape_url repeatedly.

• firecrawl__crawl_site

  Crawl a website to explore multiple pages or sub-pages. ⚠️ ASYNC OPERATION: returns a task ID — you MUST then call crawl_get_status(id) repeatedly until status='completed'. The completed response contains the crawled pages. USE THIS for multi-page research; do NOT call scrape_url repeatedly. Optional: limit (default 10

• firecrawl__search_web

  Search the web and return results from search engines. Use this when the user asks to search the internet, find information, or look something up — especially when no specific URL is provided. Can optionally scrape the content of result pages. Supports filtering by categories, country, domains, and sources.

• firecrawl__extract_data

  Extract structured fields from known URLs using a JSON Schema. Legacy endpoint - agent_extract is the recommended approach for most cases. Use this only when you have specific URLs and know exactly what fields to extract.

• firecrawl__map_site

  Map a website to discover all URLs without crawling full content. Returns a list of URLs with metadata for site exploration before full crawl.

• firecrawl__agent_extract

  AI-driven autonomous data extraction. The agent analyzes your prompt, decides which pages to visit, and extracts data accordingly. This is the RECOMMENDED approach for data extraction. Returns a task ID - use crawl_get_status to poll for results.

• firecrawl__crawl_get_status

  Get the status of an async crawl or agent_extract task. Returns the task status and results when complete.

• firecrawl__crawl_cancel

  Cancel an ongoing crawl or agent task.

• firecrawl__crawl_get_errors

  Get error details from a failed crawl or agent task for debugging.

How to connect

Firecrawl needs a provider API key to talk to firecrawl. Connect it from the Syncore dashboard:

1. Run curl -fsSL https://syncorelabs.ai/install.sh | sh on macOS / Linux (or the PowerShell command on Windows).
2. Run syncore login to create your account and a device-bound encryption key.
3. Visit syncorelabs.ai/connect and authorize Firecrawl.
4. Run syncore update to sync the skill + credentials to every installed AI client.

Pricing

Included on every Syncore tier with a per-tier shared quota — Free covers light use; Pro at $29/mo and Ultra at $99/mo unlock larger monthly allowances. Bring your own provider API key any time to bypass the Syncore quota.

See the full Syncore pricing breakdown — Free $0/mo, Pro $29/mo, Ultra $99/mo — on the homepage.