Firecrawl
Extract web data with Firecrawl
Ads
Overview
A Model Context Protocol (MCP) server that brings Firecrawl to MCP-compatible AI agents — search, scrape, and interact with the live web for clean, agent-ready context. > Big thanks to @vrknetha, @knacklabs for the initial implementation! - Search the web and get full page content - Search an index built for coding agents: GitHub issues, merged pull requests, READMEs, and docs - Scrape any URL into clean, structured data - Interact with pages — click, navigate, and operate - Deep research with autonomous agent - Automatic retries and rate limiting - Cloud and self-hosted support - SSE support
Installation
npm install -g firecrawl-mcp
Configuration
{
"mcpServers": {
"firecrawl-mcp": {
"command": "npx",
"args": ["-y", "firecrawl-mcp"],
"env": {
"FIRECRAWL_API_KEY": "YOUR-API-KEY"
}
}Capabilities
- Scrape any URL into clean data
Ask for product details, articles, or structured JSON from a single page via `firecrawl_scrape`, with options for markdown, JSON schema, or branding extraction.
- Search the web with context
Use `firecrawl_search` to find relevant pages and optionally scrape their content, with highlights, language, and country filters for targeted results.
- Map a site's URL structure
Discover all indexed URLs on a domain with `firecrawl_map` to plan what to scrape next.
- Crawl multiple pages automatically
Launch a `firecrawl_crawl` job to extract content across a site section, then check progress with `firecrawl_check_crawl_status`.
- Run autonomous deep research
Delegate complex multi-source questions to `firecrawl_agent` and poll `firecrawl_agent_status` for structured findings.
- Interact with live pages
Use `firecrawl_interact` to click, type, and navigate dynamic sites, then stop sessions with `firecrawl_interact_stop`.
Tags
- web-scraping
- firecrawl
- search
- data-analysis
- browser-automation
Related MCP servers
Skyvern
OfficialAI-powered browser automation MCP server — navigate sites, fill forms, extract data, and handle logins via Claude Code CLI
Apify
OfficialOfficial Apify MCP server for AI agents to run Actors, extract website data, and automate web scraping and crawling workflows.
Bright Data
OfficialDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Notte
OfficialLeverage Notte Web AI agents & cloud browser sessions for scalable browser automation & scraping workflows