firecrawl-scrape

Name: firecrawl-scrape
Availability: InStock
Author: parcadei

Scrape web pages and extract content via Firecrawl MCP into Markdown, HTML, or plain text.

3.9k|296|Updated Dec 23, 2025

Search Tags:#automation #MCP #firecrawl #data-extraction #web-scrape

Ready to run

npx skills add https://github.com/parcadei/Continuous-Claude --skill firecrawl-scrape

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: firecrawl-scrape
Source: https://github.com/parcadei/Continuous-Claude/tree/main/.claude/skills/firecrawl-scrape
Command: npx skills add https://github.com/parcadei/Continuous-Claude --skill firecrawl-scrape

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill scrapes web pages and extracts structured content using the Firecrawl MCP service.

Core Features & Use Cases

Web content extraction: Pull text and metadata from pages.
Search-ready outputs: Markdown or text for downstream processing.
Use Case: Gather API docs from a public site for integration.

Quick Start

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

Frequently Asked Questions about firecrawl-scrape

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I scrape web pages and extract content automatically?▼

Web page scraping extracts text, metadata, and structured content from URLs using automated tools. Firecrawl MCP handles this by fetching pages and converting them to Markdown, HTML, or plain text formats for downstream processing without manual copying.

What setup do I need to start scraping with Firecrawl?▼

Set up Firecrawl by configuring your MCP server with a FIRECRAWL_API_KEY in mcp_config.json, then run the scraper with a target URL and desired output format. The runtime harness manages authentication and format conversion automatically.

Can I use Firecrawl for extracting API documentation from public websites?▼

Yes. Firecrawl scrapes public web pages and extracts readable content as Markdown or text, making it ideal for pulling API docs, technical guides, or structured reference material from any publicly accessible URL.

What output formats does web scraping via Firecrawl support?▼

Firecrawl outputs scraped content in three formats: Markdown for structured readability, HTML for preservation of page layout, or plain text for minimal processing and downstream analysis.

Does Firecrawl work for scraping content across different domains and websites?▼

Yes. Firecrawl applies to broad web-scraping tasks across any domain by accepting direct URLs and returning extracted content. It handles site-agnostic content extraction without domain-specific configuration.