Using Firecrawl MCP in Cursor
Features
Let’s first discuss what Firecrawl MCP can do.
- Supports scraping, crawling, searching, extraction, deep research, and batch scraping
- Web scraping with JS rendering
- URL discovery and crawling
- Web search with content extraction
- Automatic retries with exponential backoff
- Efficient batch processing with built-in rate limiting
- Credit usage monitoring for cloud API
- Comprehensive logging system
- Support for both cloud and self-hosted FireCrawl instances
- Mobile/desktop viewport support
- Smart content filtering with tag inclusion/exclusion
Configuration
Configure the Firecrawl MCP Server startup command in Cursor.
1 | env FIRECRAWL_API_KEY=your-api-key npx -y firecrawl-mcp |
I only have a Mac, so Windows hasn’t been tested.
Available Tools
As you can see, Cursor has integrated all Firecrawl tools. Therefore, you only need to use natural language to communicate with Cursor and access all Firecrawl tools.
Results
Note: The more detailed the prompt, the more accurately Firecrawl tools can be called and the more accurate information you can get. I just did some simple testing here.
At the end
The AI crawler Firecrawl is good so far. If you need to crawl web page data, consider using it.