Firecrawl Scrape

A straightforward wrapper around Firecrawl's MCP server for pulling content from URLs or search queries. You pass in a URL and get back markdown, HTML, or plain text. The search mode is handy when you need Claude to grab current info without knowing the exact page. You'll need a Firecrawl API key in your MCP config, which means this isn't free to run at scale. The skill itself is thin, just a Python harness call with a couple flags, but that's fine since Firecrawl does the heavy lifting. Good for one-off scrapes or when you need cleaner extraction than curl and grep.

skills.sh installs: 492
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill firecrawl-scrape --agent claude-code

Installs into .claude/skills of the current project.

Files

Firecrawl Scrape Skill

When to Use

Scrape content from any URL
Extract structured data from web pages
Search the web and get content

Instructions

uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
    --url "https://example.com" \
    --format "markdown"

Parameters

--url: URL to scrape
--format: Output format - markdown, html, text (default: markdown)
--search: (alternative) Search query instead of direct URL

Examples

# Scrape a page
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
    --url "https://docs.python.org/3/library/asyncio.html"

# Search and scrape
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
    --search "Python asyncio best practices 2024"