@Sacode
基本情報
MCP server for Firecrawl Simple — a web scraping and site mapping tool enabling LLMs to access and process web content
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"firecrawl-simple-mcp": {
"command": "npx",
"args": [
"-y",
"firecrawl-simple-mcp"
],
"env": {
"FIRECRAWL_API_URL": "http://localhost:3002/v1"
}
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
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.
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).
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.
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.
Verify the Firecrawl Simple API is running, check the API URL (including `/v1`), and ensure no network restrictions block the connection.
The server supports `stdio` (default) and `sse` transport types. Set `FIRECRAWL_TRANSPORT_TYPE` to switch between them.
Ensure `FIRECRAWL_API_KEY` is correct and matches the API’s requirements. Contact the API administrator if needed.
Give your AI agent its own proxies. QuantumProxies exposes residential, mobile, datacenter, ISP and IPv6 endpoints as MCP tools: list your plans, generate ready-to-use proxy strings with credentials, target by country, s
The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.
Loadster is a load testing, stress testing, and synthetic monitoring platform. Run Playwright, Browser Bots, and Protocol Bots to test and monitor your websites, web apps, and APIs. Loadster MCP gives your agents the abi
Helps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.
A flexible HTTP fetching Model Context Protocol server.
コメント