Skip to main content
ClaudeWave
EN, English
firecrawl / MCP Servers · Official registry

firecrawl-mcp-server

Official Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client.

  • 7.7k stars
  • 917 forks
  • 183 open issues
  • Language: JavaScript
  • License: MIT
  • updated
Install in ClaudeView on GitHub

Install

remote
Terminal
claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp
.mcp.json (project scope)
{
  "mcpServers": {
    "firecrawl": {
      "type": "http",
      "url": "https://mcp.firecrawl.dev/v2/mcp"
    }
  }
}

Remote server, no local binary. If it asks for credentials, follow the provider's README.

  1. Run the command in your terminal (Claude Code), or add the URL as a connector (Claude Desktop) or in mcp.json (Cursor).
  2. Authorise access when the client asks.
  3. Restart the session: the server's tools show up automatically.

Editor's note

The official Firecrawl MCP Server is a JavaScript-based Model Context Protocol server that gives MCP-compatible AI clients, including Claude Desktop, live access to the web through Firecrawl's API. It exposes tools for scraping any URL into clean structured data, conducting web searches that return full page content, performing multi-step browser interactions such as clicking and navigating, and running deep autonomous research tasks across multiple pages. Built-in automatic retries and rate limiting handle unreliable connections, and the server supports both the Firecrawl cloud API and self-hosted Firecrawl instances via a single environment variable switch. It can be added to Claude Desktop through Smithery's one-command installer or configured manually with npx, and it also works in Cursor, Windsurf, and VS Code. A notable detail is the SSE and Streamable HTTP transport support, which allows the server to run as a local HTTP endpoint at localhost:3000 rather than the default stdio mode. Developers, researchers, and data engineers who need an AI agent to retrieve and process live web content are the primary audience.

README

MCP Servers overview

README preview not available. Visit the repo on GitHub for full documentation.
Use cases
Automation AI / ML
Topics
batch-processingclaudecontent-extractiondata-collectionfirecrawlfirecrawl-aigemini-cli-extensionjavascript-renderingllm-toolsmcpmcp-servermodel-context-protocolsearch-apiweb-crawlerweb-scraping
Frequently asked

What people ask about firecrawl-mcp-server

What is firecrawl/firecrawl-mcp-server?

firecrawl/firecrawl-mcp-server is mcp servers for the Claude AI ecosystem. Official Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client. It has 7.7k GitHub stars and its last recorded update is dated 2026-10-23.

How do I install firecrawl-mcp-server?

You can install firecrawl-mcp-server by cloning the repository (https://github.com/firecrawl/firecrawl-mcp-server) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is firecrawl/firecrawl-mcp-server safe to use?

Our security agent has analyzed firecrawl/firecrawl-mcp-server and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains firecrawl/firecrawl-mcp-server?

firecrawl/firecrawl-mcp-server is maintained by firecrawl. The last recorded GitHub activity is dated 2026-10-23, with 183 open issues.

Are there alternatives to firecrawl-mcp-server?

Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.

Project homepage
https://firecrawl.dev