firecrawl-mcp-server
Powerful web crawling and search capabilities, suitable for LLM clients like Cursor and Claude.
- Type
- MCP
- Open source
- Yes
- GitHub Stars
- ★ 6.7k
- Source
- mcp-github
Overview
Firecrawl MCP Server is a Model Context Protocol (MCP) server that brings Firecrawl's web crawling and search functionality into AI agents that support MCP. Through this server, AI can retrieve full webpage content, extract structured data, and interact with pages. Ideal for AI applications requiring real-time information from the internet. Integration options include command-line installation via npx or configuration in platforms like Cursor and Windsurf.
Capabilities
- ▪Full webpage content search
- ▪URL-structured data extraction
- ▪Page interaction operations
- ▪Automatic retry and rate limiting
- ▪Cloud and self-hosted support
Use cases
Setup
env FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get an API Key?
Create an account and get your key at https://www.firecrawl.dev/app/api-keys.
Which platforms are supported?
Supports Cursor, Windsurf, VS Code, and more.
Related skills
Scrapling
An adaptive web scraping framework capable of handling everything from single requests to large-scale scraping.
TrendRadar
An AI-driven tool for sentiment monitoring and trend analysis, supporting multi-platform aggregation, RSS subscription, and intelligent notifications.
gpt-researcher
An autonomous agent for deep research using any LLM provider.
Deep-Research-skills
Provides structured deep research capabilities for Claude Code, OpenCode, and Codex, supporting a two-phase research process.
user-research-skill
Provides end-to-end user research capabilities for AI agents, including interviews, synthetic users, and quantitative surveys.
google-maps-scraper
Scrape business data from Google Maps, such as name, address, phone number, etc.