firecrawl-mcp-server
Enables LLM-driven automation to extract structured data from websites and search results in real-time, reducing manual data collection overhead and accelera…
Official Firecrawl MCP server. Gives Claude and other MCP clients web search, URL scraping into clean structured data, page interaction (click, navigate, operate), and deep research via the Firecrawl API. Supports cloud-hosted and self-hosted Firecrawl, with automatic retries and rate limiting.
- Ask Claude to scrape a competitor's pricing page and extract all product tiers and costs.
- Generate a dataset by crawling multiple documentation sites and collecting API endpoint definitions.
- Automate extraction of job listings from career pages across several company websites.
Enables LLM-driven automation to extract structured data from websites and search results in real-time, reducing manual data collection overhead and accelerating research-driven development workflows.
Engineering teams building LLM-powered applications or automations that require live web data integration.
https://github.com/firecrawl/firecrawl-mcp-server
By firecrawl
How to Get It
claude mcp add firecrawl-mcp --env FIRECRAWL_API_KEY=fc-YOUR_API_KEY -- npx -y firecrawl-mcp
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Scrape a competitor's pricing page and extract all product tiers and costs
Trust Signals Auto-scanned
Data & Access
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 6,452 GitHub stars; contributors unknown; last commit 3d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 6,452 GitHub stars; contributors unknown; last commit 3d ago; license MIT.