Firecrawl Simple MCP Server

@Sacode

代码仓库

基本信息

分类

浏览器自动化

许可证

MIT license

传输方式

stdio

作者

Sacode

关于 Firecrawl Simple MCP Server

MCP server for Firecrawl Simple — a web scraping and site mapping tool enabling LLMs to access and process web content

#nodejs #ai #mcp #web-scraping #llm #firecrawl#site-mapping

Firecrawl Simple MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "firecrawl-simple-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-simple-mcp"
      ],
      "env": {
        "FIRECRAWL_API_URL": "http://localhost:3002/v1"
      }
    }
  }
}

Firecrawl Simple MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Firecrawl Simple MCP Server?

Firecrawl Simple MCP Server is a Model Context Protocol (MCP) server for Firecrawl Simple, a web scraping and site mapping tool that enables Large Language Models (LLMs) to access and process web content. It is designed for developers integrating web data into AI applications.

How to use Firecrawl Simple MCP Server?

Install globally via npm install -g firecrawl-simple-mcp, then run with environment variables like FIRECRAWL_API_URL (default http://localhost:3002/v1). It can be configured for use with Claude Desktop or Cursor by adding it as an MCP server in their configuration files. For SSE transport, set FIRECRAWL_TRANSPORT_TYPE=sse and the server listens on the port specified by FIRECRAWL_SERVER_PORT (default 3003).

Key features of Firecrawl Simple MCP Server

Web scraping with JavaScript rendering support.
Generate sitemaps of any website.
Simplified architecture with consistent error handling.
Strong type safety with Zod schema validation.
Configurable via environment variables.

Use cases of Firecrawl Simple MCP Server

Scrape a single webpage for LLM context extraction.
Map a website’s structure to understand its content hierarchy.
Integrate web scraping into AI assistants like Claude or Cursor.

常见问题

How do I configure the Firecrawl Simple MCP Server?

Set environment variables such as `FIRECRAWL_API_URL`, `FIRECRAWL_API_KEY`, `FIRECRAWL_API_TIMEOUT`, `FIRECRAWL_SERVER_PORT`, `FIRECRAWL_TRANSPORT_TYPE`, and `FIRECRAWL_LOG_LEVEL`. Default values are provided in the configuration table.

Why was crawl functionality removed?

Crawl was removed to prevent context overflow for LLMs (too much information), because crawling runs asynchronously (unsuitable for synchronous MCP), and to align with primary documentation. For multi-page scraping, use the scrape tool with individual URLs or implement a custom solution.