Firecrawl MCP Server
by MCP-Mirror
The Firecrawl MCP Server is a Model Context Protocol (MCP) server implementation designed to integrate with Firecrawl for enhanced web scraping capabilities. It provides tools for scraping, crawling, searching, and extracting data from the web.
Last updated: N/A
What is Firecrawl MCP Server?
The Firecrawl MCP Server is an implementation of the Model Context Protocol that leverages Firecrawl to offer a suite of web scraping tools. It allows users to scrape content from websites, crawl through multiple pages, perform web searches with content extraction, and extract structured information using LLMs. It supports both cloud and self-hosted FireCrawl instances.
How to use Firecrawl MCP Server?
To use the Firecrawl MCP Server, you can install it via npm or npx. Configuration involves setting environment variables such as FIRECRAWL_API_KEY for cloud API usage or FIRECRAWL_API_URL for self-hosted instances. It can be integrated with tools like Cursor, Windsurf, and Claude Desktop by configuring the MCP server settings and providing the necessary command and environment variables. Available tools include scrape, batch scrape, check batch status, search, crawl, and extract.
Key features of Firecrawl MCP Server
Scrape, crawl, search, extract, deep research and batch scrape support
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 cloud and self-hosted FireCrawl instances
Mobile/Desktop viewport support
Smart content filtering with tag inclusion/exclusion
Use cases of Firecrawl MCP Server
Automated data extraction from e-commerce websites for price comparison
Web crawling for lead generation and contact information gathering
Content aggregation from multiple sources for research purposes
Monitoring news articles for specific keywords and trends
Extracting structured data from web pages using LLM capabilities
FAQ from Firecrawl MCP Server
What is the purpose of the FIRECRAWL_API_KEY environment variable?
What is the purpose of the FIRECRAWL_API_KEY environment variable?
The FIRECRAWL_API_KEY is required when using the cloud API to authenticate your requests. It is optional when using a self-hosted instance with FIRECRAWL_API_URL.
How do I configure the server for a self-hosted FireCrawl instance?
How do I configure the server for a self-hosted FireCrawl instance?
Set the FIRECRAWL_API_URL environment variable to the URL of your self-hosted instance. Optionally, you can also set FIRECRAWL_API_KEY if your instance requires authentication.
What are the available tools in the Firecrawl MCP Server?
What are the available tools in the Firecrawl MCP Server?
The available tools include firecrawl_scrape (scrape a single URL), firecrawl_batch_scrape (scrape multiple URLs), firecrawl_check_batch_status (check batch operation status), firecrawl_search (search the web), firecrawl_crawl (start a web crawl), and firecrawl_extract (extract structured information using LLMs).
How does the server handle rate limiting?
How does the server handle rate limiting?
The server uses FireCrawl's built-in rate limiting and implements automatic retries with exponential backoff to avoid overwhelming the API.
How can I monitor credit usage for the cloud API?
How can I monitor credit usage for the cloud API?
The server provides credit usage monitoring with warning and critical thresholds. You can configure these thresholds using the FIRECRAWL_CREDIT_WARNING_THRESHOLD and FIRECRAWL_CREDIT_CRITICAL_THRESHOLD environment variables.