Firecrawl MCP
About
Firecrawl's official MCP server. Gives agents powerful web scraping capabilities: JS rendering, full-site crawling, search and structured data extraction with clean Markdown output.
Our Verdict
Firecrawl MCP brings data capabilities to the MCP ecosystem. Its GitHub popularity reflects community trust, and the standardized protocol ensures broad compatibility across AI clients.
Pricing
Use Cases
- Integrating data capabilities into AI agent workflows
- Building custom AI-powered tools with Firecrawl MCP
- Enhancing AI agent functionality with standardized MCP access
Pros
- Firecrawl MCP provides standardized MCP protocol access
- Open source with 7,094 GitHub stars
- Active development and community support
Cons
- Requires MCP-compatible client (Claude, Cursor, etc.)
- Setup complexity varies by client
- Some features may depend on client capabilities
Installation
env FIRECRAWL_API_KEY=<key> npx -y firecrawl-mcpFrequently Asked Questions
How is Firecrawl MCP different from ordinary web scraping?
It is built for LLMs: scraped pages come back as clean Markdown, with support for JS-rendered pages, full-site crawling, search and structured extraction. The AI gets citation-ready content instead of raw HTML.
How do I install Firecrawl MCP?
Sign up at firecrawl.dev for an API key, then run env FIRECRAWL_API_KEY=<key> npx -y firecrawl-mcp in your MCP configuration. Cursor, Claude Code, Windsurf and VS Code are all supported.
Does Firecrawl cost money?
The MCP server itself is open source and free, but scraping runs through the Firecrawl cloud API: the free plan includes a one-time 500-credit allowance, enough for light use. Heavy crawling requires a paid credit plan, or you can self-host the open-source version.