Firecrawl MCP Server logo

Firecrawl MCP Server

by MCP-Mirror

Firecrawl MCP Server is a Model Context Protocol (MCP) server implementation that integrates with Firecrawl for web scraping capabilities. It provides tools for scraping, crawling, searching, and extracting data from the web.

View on GitHub

Last updated: N/A

What is Firecrawl MCP Server?

The Firecrawl MCP Server is an implementation of the Model Context Protocol that leverages Firecrawl's web scraping capabilities. It provides a set of tools accessible through a command-line interface or integrations with platforms like Cursor and Windsurf, allowing users to scrape, crawl, search, and extract data from websites efficiently.

How to use Firecrawl MCP Server?

To use the Firecrawl MCP Server, you can install it globally via npm or run it directly with npx. You'll need a Firecrawl API key for cloud API usage, which you can set as an environment variable. The server can then be integrated with tools like Cursor, Windsurf, or Claude Desktop by configuring it as an MCP server with the appropriate command and environment variables. Available tools include scrape, batch scrape, check batch status, search, crawl, and extract, each with specific arguments to control their behavior.

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 for market research

  • Content aggregation from multiple websites

  • Lead generation through web scraping

  • Monitoring competitor pricing and product information

  • Building datasets for machine learning models

FAQ from Firecrawl MCP Server

What is the purpose of the FIRECRAWL_API_KEY environment variable?

The FIRECRAWL_API_KEY environment variable is required when using the cloud API to authenticate your requests to Firecrawl's services. It is optional when using a self-hosted instance with the FIRECRAWL_API_URL.

How do I configure the server to use a self-hosted Firecrawl instance?

To use a self-hosted Firecrawl instance, set the FIRECRAWL_API_URL environment variable to the URL of your self-hosted instance. You may also need to set the FIRECRAWL_API_KEY if your instance requires authentication.

What are the default retry settings and how can I customize them?

By default, the server retries failed requests up to 3 times with exponential backoff. The initial delay is 1 second, the maximum delay is 10 seconds, and the backoff factor is 2. You can customize these settings using the FIRECRAWL_RETRY_MAX_ATTEMPTS, FIRECRAWL_RETRY_INITIAL_DELAY, FIRECRAWL_RETRY_MAX_DELAY, and FIRECRAWL_RETRY_BACKOFF_FACTOR environment variables.

How does the server handle rate limiting?

The server automatically handles rate limiting by retrying requests with exponential backoff. This helps avoid overwhelming the API and ensures that requests are eventually processed.

What is the purpose of the credit usage monitoring feature?

The credit usage monitoring feature tracks your API credit consumption for cloud API usage and provides warnings at specified thresholds. This helps prevent unexpected service interruption due to credit exhaustion. You can configure the warning and critical thresholds using the FIRECRAWL_CREDIT_WARNING_THRESHOLD and FIRECRAWL_CREDIT_CRITICAL_THRESHOLD environment variables.