Overview

MCP Server FireCrawl

MCP Server FireCrawl is a Model Context Protocol server implementation designed for advanced web scraping capabilities. The server integrates with FireCrawl to provide comprehensive web data extraction features.

Key Features

Core Capabilities

• JavaScript-enabled web scraping
• Batch processing with parallel execution
• URL discovery and crawling functionality
• Web search with content extraction
• Smart content filtering with tag controls

Technical Infrastructure

• Automatic retry mechanism with exponential backoff
• Credit usage monitoring for cloud API
• Comprehensive logging system
• Support for both cloud and self-hosted instances

Installation Options

Quick Setup

npx -y @smithery/cli install mcp-server-firecrawl --client claude

Manual Setup

npm install -g mcp-server-firecrawl

Available Tools

The server provides five main tools:

Scraping Tools

• fire_crawl_scrape: Single URL content extraction
• fire_crawl_batch_scrape: Multiple URL parallel processing
• fire_crawl_check_batch_status: Batch operation monitoring
• fire_crawl_search: Web search with content extraction
• fire_crawl_crawl: Asynchronous web crawling

System Parameters

Rate Limiting

• Free tier: 3 requests per minute
• Automatic retry system
• Parallel processing support
• Configurable batch operations with 2-second delays between requests

Error Management The system implements comprehensive error handling with automatic retries, rate limit management, and detailed error reporting. All operations are monitored through a robust logging system that tracks performance metrics, credit usage, and rate limits.

The project is available under the MIT License and welcomes community contributions through pull requests.