vrknetha_mcp-server-firecrawl
FireCrawl MCP Server is a Model Context Protocol server implementation that integrates with FireCrawl for advanced web scraping capabilities.
FireCrawl MCP Server
A Model Context Protocol (MCP) server implementation that integrates with FireCrawl for advanced web scraping capabilities.
Features
- JavaScript Rendering: Extract content from JavaScript-heavy websites
- Mobile/Desktop Views: Support for different viewport configurations
- Smart Rate Limiting: Built-in rate limit handling
- Multiple Formats: Support for HTML, Markdown, screenshots, and raw text extraction
- Batch Processing: Efficient handling of multiple URLs
- Content Filtering: Include or exclude specific HTML tags
Tools
fire_crawl_scrape
Scrapes content from a single URL with customizable options.
- Inputs:
url
(string): Target URL to scrapeformats
(array): Output formats (markdown
,html
,rawHtml
,screenshot
,links
,screenshot@fullPage
,extract
)waitFor
(number, optional): Wait time in millisecondsonlyMainContent
(boolean, optional): Extract main content onlyincludeTags
(array, optional): HTML tags to specifically includeexcludeTags
(array, optional): HTML tags to excludemobile
(boolean, optional): Use mobile viewportskipTlsVerification
(boolean, optional): Skip TLS verification
fire_crawl_batch
Initiates a batch scraping job for multiple URLs.
- Inputs:
urls
(array): List of URLs to scrapeformats
(array): Output formats (same as single scrape)- Other options same as
fire_crawl_scrape
fire_crawl_status
Checks the status of a batch scraping job.
- Inputs:
id
(string): Batch job ID to check
Installation
npm install mcp-server-firecrawl
Configuration
Getting an API Key
- Sign up for a FireCrawl account
- Generate your API key from the dashboard
- Set the API key in your environment
Usage with Claude Desktop
Add this to your claude_desktop_config.json
:
{
"mcpServers": {
"mcp-server-firecrawl": {
"command": "npx",
"args": ["-y", "mcp-server-firecrawl"],
"env": {
"FIRE_CRAWL_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
Development
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
Rate Limits
- 3 requests per minute on free tier
- 25-second cooldown after hitting rate limit
- Higher limits available on paid plans
License
MIT License - see LICENSE file for details
Related MCP Servers
View all browser_automation servers →Fetch
by modelcontextprotocol
A Model Context Protocol server that provides web content fetching capabilities, enabling LLMs to retrieve and process content from web pages.
markdownify-mcp
by zcaceres
Markdownify is a Model Context Protocol (MCP) server that converts various file types and web content to Markdown format.
mcp-playwright
by executeautomation
A Model Context Protocol server that provides browser automation capabilities using Playwright.
cursor-talk-to-figma-mcp
by sonnylazuardi
This project implements a Model Context Protocol (MCP) integration between Cursor AI and Figma, allowing Cursor to communicate with Figma for reading designs and modifying them programmatically.
playwright-mcp
by microsoft
A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright.
ai-agent-marketplace-index-mcp
by AI-Agent-Hub
MCP Server for AI Agent Marketplace Index from DeepNLP, allowing AI assistants to search available AI agents by keywords or categories.
web-eval-agent
by Operative-Sh
operative.sh's MCP Server is a browser-use powered agent that autonomously executes and debugs web apps directly in your code editor.