# Firecrawl MCP Server

> Firecrawl MCP server turns websites into clean, LLM-ready data by scraping URLs into markdown or structured JSON, crawling sites, searching the web, extracting structured data, and providing browser interaction tools. It offers 13+ tools including scraping, crawling, mapping, extraction, agent-based research, and persistent browser sessions for multi-step automation. Widely used for web research, competitor audits, and data gathering directly in AI coding environments.

- **URL:** https://github.com/mendableai/firecrawl
- **Category:** Web Scraping
- **Tags:** Web Scraping, Content Extraction, Browser Automation
- **Featured:** yes
- **Updated:** 2026-04-22 20:55
- **Canonical page:** https://mcpserver.ever.works/es/items/firecrawl-mcp-server

## Details

## Features

- **firecrawl_scrape**: Scrape any URL into clean markdown or structured JSON with options for mobile rendering, tag filtering, JavaScript waiting.
- **firecrawl_search**: Web search with content extraction and time-based filtering.
- **firecrawl_crawl / firecrawl_check_crawl_status**: Asynchronous site crawling with depth, deduplication, domain constraints.
- **firecrawl_map**: Discover indexed URLs on a site.
- **firecrawl_extract**: LLM-based structured data extraction using JSON schema.
- **firecrawl_agent / firecrawl_agent_status**: Autonomous research agent for browsing, searching, compiling reports.
- **firecrawl_interact**: Interactive page actions like clicking, form filling using natural language or Playwright; supports logged-in sessions.
- **firecrawl_browser_* tools**: Persistent browser session management via CDP.

## Pricing

Free tier available; paid plans start at $16/month.

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://mcpserver.ever.works/es/items/firecrawl-mcp-server._